© 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. 13733
    Prev
    Next
    INDEX
    Explanations

    concern related phrases

    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
    +0.25
    0.8%
    356
    +0.15
    0.5%
    401
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.25
    0.08
    473
    +0.15
    0.07
    370
    +0.15
    0.07
    Negative Logits
    orse
    -1.08
    atoon
    -1.04
    arine
    -1.00
    kat
    -0.94
    ornia
    -0.94
    orses
    -0.93
    istries
    -0.91
    mma
    -0.91
    pat
    -0.90
    priv
    -0.90
    POSITIVE LOGITS
     nonetheless
    2.02
     nevertheless
    1.96
     persisted
    1.28
     still
    1.22
     alas
    1.18
     persists
    1.18
    etheless
    1.18
     also
    1.18
    theless
    1.16
     retained
    1.11
    Activations Density 2.390%

    No Known Activations