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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1339
    Prev
    Next
    INDEX
    Explanations

    words related to tendencies or inclinations

    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
    195
    +0.24
    0.8%
    7
    +0.19
    0.7%
    597
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.24
    0.03
    7
    +0.19
    0.05
    597
    +0.15
    0.04
    Negative Logits
    lain
    -1.11
    gur
    -1.05
    arta
    -1.02
     Industry
    -0.88
    fil
    -0.87
    ZA
    -0.86
    gran
    -0.85
     Chall
    -0.83
    ilings
    -0.83
    ahu
    -0.83
    POSITIVE LOGITS
    rils
    1.66
    entious
    1.38
    ril
    1.33
    entimes
    1.29
    ensical
    1.10
    erest
    1.08
     toward
    1.08
    erers
    1.08
    Ń·
    1.08
     grav
    1.02
    Activations Density 0.705%

    No Known Activations