Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 781
    Prev
    Next
    INDEX
    Explanations

    information related to technology and software

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    640
    +0.38
    1.9%
    160
    +0.16
    0.8%
    107
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.38
    0.36
    160
    +0.16
    0.28
    442
    +0.11
    0.25
    Negative Logits
     negoti
    -0.81
     veter
    -0.78
     dispar
    -0.74
     dece
    -0.72
    xual
    -0.72
     renown
    -0.70
     overr
    -0.70
     ousted
    -0.69
     exha
    -0.69
    utic
    -0.68
    POSITIVE LOGITS
    Contents
    1.10
    Click
    1.10
    Chapter
    1.08
    ********************************
    1.08
    Download
    1.08
    Reviewer
    1.08
    Subscribe
    1.07
    Rating
    1.07
    Spoiler
    1.06
    Related
    1.06
    Activations Density 1.645%

    No Known Activations