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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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 Local
    5. 6-RES_SCL-AJT
    6. 13222
    Prev
    Next
    INDEX
    Explanations

    information related to upcoming events, schedules, and news updates within a specific community

    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
    592
    +0.09
    0.5%
    468
    +0.08
    0.5%
    398
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.09
    0.28
    288
    +0.08
    0.27
    115
    +0.08
    0.13
    Negative Logits
    lord
    -0.53
    esson
    -0.52
    rites
    -0.51
    vati
    -0.49
    lords
    -0.49
     Anthem
    -0.48
     Carnage
    -0.48
     Tale
    -0.47
     Clown
    -0.46
     Pupp
    -0.45
    POSITIVE LOGITS
    PDF
    0.62
     captcha
    0.59
     ILCS
    0.58
     CLICK
    0.58
    HTML
    0.57
    embed
    0.56
     html
    0.56
    ascript
    0.56
    ĨĴ
    0.55
     eBook
    0.55
    Activations Density 13.184%

    No Known Activations