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. 4425
    Prev
    Next
    INDEX
    Explanations

    information related to financial matters and government policies

    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
    459
    +0.13
    0.6%
    447
    +0.13
    0.6%
    709
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.29
    373
    +0.13
    -0.14
    64
    +0.10
    -0.15
    Negative Logits
    agus
    -0.76
    duct
    -0.73
     è£ıç
    -0.73
    ranch
    -0.71
    ãĥ³ãĤ¸
    -0.67
    ochond
    -0.64
    ASE
    -0.62
    iotic
    -0.62
    ultimate
    -0.61
    orum
    -0.61
    POSITIVE LOGITS
    birth
    0.80
    noon
    0.77
    adays
    0.76
    heres
    0.76
     reeling
    0.76
    creen
    0.67
    Enjoy
    0.66
     unanswered
    0.66
     undecided
    0.65
     technically
    0.65
    Activations Density 6.362%

    No Known Activations