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. 312
    Prev
    Next
    INDEX
    Explanations

    mentions of the Federal Reserve (Fed) or related terms

    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
    288
    +0.21
    0.7%
    526
    +0.18
    0.6%
    187
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.10
    343
    +0.18
    0.06
    326
    +0.16
    0.07
    Negative Logits
    lust
    -0.95
    âĢ¢âĢ¢
    -0.92
    FREE
    -0.91
    SPONSORED
    -0.88
    WAYS
    -0.86
     Referred
    -0.84
     Sora
    -0.84
    IBLE
    -0.84
    lihood
    -0.84
    Companies
    -0.83
    POSITIVE LOGITS
    erer
    1.53
    ricular
    1.39
    bledon
    1.34
    ollar
    1.29
    liction
    1.27
    rique
    1.24
    rik
    1.21
    eli
    1.20
    rand
    1.19
    ric
    1.17
    Activations Density 1.066%

    No Known Activations