© 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. 14084
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, possibly including names and titles

    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
    167
    +0.21
    0.8%
    326
    +0.20
    0.7%
    8
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.06
    659
    +0.20
    0.04
    167
    +0.13
    0.01
    Negative Logits
    ãģĨ
    -1.01
    ISC
    -1.01
    mberg
    -0.99
     Across
    -0.98
    nikov
    -0.91
    giving
    -0.83
    âĶģ
    -0.83
     Enabled
    -0.83
     abiding
    -0.82
    anwhile
    -0.82
    POSITIVE LOGITS
    cci
    1.19
    pling
    1.18
    ching
    1.17
    plet
    1.15
    alog
    1.14
    Pont
    1.13
    gey
    1.13
    iple
    1.08
    illard
    1.08
    pee
    1.07
    Activations Density 0.774%

    No Known Activations