© 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. 14673
    Prev
    Next
    INDEX
    Explanations

    words related to behaviors and activities

    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
    360
    +0.12
    0.5%
    597
    +0.12
    0.5%
    13
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.12
    0.13
    195
    +0.12
    0.04
    665
    +0.12
    0.11
    Negative Logits
    issance
    -0.82
    éĹ
    -0.78
     helicop
    -0.71
     exha
    -0.69
     afore
    -0.68
    olesc
    -0.67
     enthusi
    -0.66
    ophy
    -0.65
    isal
    -0.65
     Moroc
    -0.65
    POSITIVE LOGITS
    ingly
    1.16
    ings
    1.07
     themselves
    1.01
    fully
    1.00
    eth
    0.85
    ously
    0.82
    ilies
    0.80
     alike
    0.80
    backs
    0.79
    adelphia
    0.78
    Activations Density 2.936%

    No Known Activations