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

    Neuronpedia

    APICircuit 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. 45382
    Prev
    Next
    INDEX
    Explanations

    words related to business and economic activities

    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
    +0.35
    1.6%
    459
    +0.12
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.35
    0.49
    64
    +0.12
    -0.34
    618
    +0.10
    0.23
    Negative Logits
     nig
    -0.77
     inflic
    -0.66
    tumblr
    -0.65
     ransom
    -0.65
     afore
    -0.64
     Whats
    -0.63
    leted
    -0.61
     onward
    -0.60
     Pastebin
    -0.59
     removable
    -0.59
    POSITIVE LOGITS
    odox
    0.75
    uer
    0.69
     Architects
    0.69
    olor
    0.68
    sd
    0.68
    ullivan
    0.67
    ulty
    0.66
     Distribut
    0.66
    enegger
    0.65
    letcher
    0.65
    Activations Density 23.555%

    No Known Activations