© 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. 5007
    Prev
    Next
    INDEX
    Explanations

    information related to sports events and figures, especially in the context of social issues and community engagement

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.13
    0.7%
    326
    +0.11
    0.6%
    201
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.24
    201
    +0.11
    0.10
    288
    +0.11
    0.21
    Negative Logits
    undai
    -0.67
    phis
    -0.62
    ļ
    -0.62
    atem
    -0.61
    Ħ¢
    -0.59
    ractor
    -0.59
    fman
    -0.59
    į
    -0.58
    rative
    -0.58
    anooga
    -0.58
    POSITIVE LOGITS
     Wade
    0.78
     Bauer
    0.65
     Phillips
    0.60
     Bosh
    0.58
    nesday
    0.57
    beck
    0.55
     Hole
    0.55
     Hampton
    0.53
     Davis
    0.53
     Heat
    0.52
    Activations Density 9.386%

    No Known Activations