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. 425
    Prev
    Next
    INDEX
    Explanations

    phrases related to careers and personal journeys

    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
    393
    +0.20
    0.6%
    671
    +0.15
    0.5%
    37
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.20
    0.07
    717
    +0.15
    0.05
    362
    +0.14
    0.06
    Negative Logits
    enance
    -1.21
     rooft
    -1.07
    osponsors
    -0.94
     Abbott
    -0.91
     surfaces
    -0.86
     Kahn
    -0.86
     tips
    -0.86
     Fiorina
    -0.85
     sums
    -0.85
    tar
    -0.84
    POSITIVE LOGITS
     journey
    1.29
     countdown
    1.23
     careers
    1.11
     fray
    1.09
    ciating
    1.08
     dialogue
    1.07
    sembly
    1.07
     dialog
    1.07
     conversation
    1.05
    mble
    1.05
    Activations Density 1.139%

    No Known Activations