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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13878
    Prev
    Next
    INDEX
    Explanations

    references to aircraft taking off

    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
    152
    +0.20
    0.6%
    373
    +0.16
    0.5%
    501
    +0.15
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.20
    0.04
    501
    +0.16
    0.03
    271
    +0.15
    0.03
    Negative Logits
    ophon
    -1.05
    ocene
    -1.04
    %]
    -1.04
    geries
    -1.01
    Gall
    -0.97
    hai
    -0.97
    isma
    -0.97
    etus
    -0.97
    zanne
    -0.96
    jad
    -0.95
    POSITIVE LOGITS
    spr
    1.18
     pist
    1.16
    screen
    1.15
     steam
    1.15
    shoot
    1.14
    loaded
    1.09
    nings
    1.07
    cffffcc
    1.00
     leash
    0.99
    loading
    0.99
    Activations Density 0.233%

    No Known Activations