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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13451
    Prev
    Next
    INDEX
    Explanations

    cryptic messages hidden within texts

    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
    163
    +0.18
    0.6%
    527
    +0.18
    0.6%
    130
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.07
    163
    +0.18
    0.06
    67
    +0.16
    0.07
    Negative Logits
    lihood
    -1.07
    姫
    -0.96
    heid
    -0.95
    folk
    -0.94
    ropolitan
    -0.92
    chest
    -0.92
     Polo
    -0.92
    coming
    -0.90
    Materials
    -0.89
     Ukrainian
    -0.88
    POSITIVE LOGITS
    adle
    1.25
    umb
    1.23
    umbled
    1.22
    umbs
    1.19
    utch
    1.18
    atism
    1.13
    usted
    1.12
    ump
    1.10
    umbles
    1.10
    anium
    1.09
    Activations Density 1.315%

    No Known Activations