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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 487
    Prev
    Next
    INDEX
    Explanations

    the word "waiting" 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
    566
    +0.17
    0.5%
    200
    +0.15
    0.5%
    288
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.17
    0.06
    200
    +0.15
    0.05
    32
    +0.15
    0.05
    Negative Logits
    insula
    -1.13
    jac
    -1.12
    audi
    -1.11
    mp
    -1.10
    sports
    -1.02
    reb
    -0.98
    rylic
    -0.97
    cer
    -0.97
    iverpool
    -0.96
     Yugoslavia
    -0.96
    POSITIVE LOGITS
     patiently
    1.89
     anx
    1.28
     impatient
    1.23
     eagerly
    1.23
    eful
    1.22
     waits
    1.21
     wait
    1.17
     waiting
    1.16
     waited
    1.16
     suspense
    1.16
    Activations Density 1.127%

    No Known Activations