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. 4220
    Prev
    Next
    INDEX
    Explanations

    words related to financial debt and deficits

    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
    +0.24
    1.0%
    459
    +0.13
    0.5%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.18
    48
    +0.13
    0.09
    9
    +0.13
    0.08
    Negative Logits
    £ı
    -1.08
     Flavoring
    -0.87
    theless
    -0.83
    Ĥ¬
    -0.80
    ertain
    -0.78
    ISTER
    -0.73
    WAYS
    -0.72
    ·
    -0.72
    Ale
    -0.71
    zbek
    -0.70
    POSITIVE LOGITS
     repayment
    1.35
     repay
    1.15
     debt
    1.10
     forgiveness
    1.10
     incurred
    1.10
     repaid
    1.02
     collectors
    1.01
    ors
    1.00
     owed
    0.97
     collector
    0.96
    Activations Density 6.682%

    No Known Activations