© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 33843
    Prev
    Next
    INDEX
    Explanations

    information related to news articles and updates, particularly focusing on specific individuals or events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Layer 6 UMAP region: e2e-recon outlier bottom right - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.33
    4.1%
    640
    +0.09
    1.1%
    138
    +0.09
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.33
    0.67
    393
    +0.09
    0.73
    480
    +0.09
    -0.40
    Negative Logits
     reper
    -0.28
     circulation
    -0.28
    ilty
    -0.28
     estranged
    -0.28
     eleph
    -0.28
     embargo
    -0.28
     amnesty
    -0.28
    ropri
    -0.27
    atively
    -0.27
     obligation
    -0.27
    POSITIVE LOGITS
    CLOSE
    0.52
    Untitled
    0.51
    Abstract
    0.51
    WASHINGTON
    0.50
    Description
    0.49
    CTV
    0.47
    Overview
    0.47
    SAN
    0.46
    Still
    0.46
    Trivia
    0.44
    Activations Density 82.984%

    No Known Activations