© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 6289
    Prev
    Next
    INDEX
    Explanations

    texts related to sports and political commentary

    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
    98
    +0.16
    0.5%
    588
    +0.16
    0.5%
    666
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.16
    0.05
    244
    +0.16
    0.05
    718
    +0.14
    0.05
    Negative Logits
    staking
    -1.31
    ALD
    -1.13
    çͰ
    -1.13
    ãĤ´
    -1.12
     subur
    -1.12
    mud
    -1.10
     eleph
    -1.08
    ãĥī
    -1.07
    ãĤŃ
    -1.07
    accompanied
    -1.07
    POSITIVE LOGITS
     consolation
    1.20
     takeaway
    1.04
     Interstellar
    1.03
     tribute
    1.00
     misfortune
    0.97
     glory
    0.96
    chance
    0.96
     greatness
    0.95
    adium
    0.94
     Starg
    0.93
    Activations Density 0.652%

    No Known Activations