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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7602
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to software development, hardware components, and programming languages

    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
    447
    +0.27
    0.9%
    419
    +0.16
    0.5%
    326
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.27
    0.07
    731
    +0.16
    0.04
    176
    +0.15
    0.04
    Negative Logits
    20439
    -0.98
    entin
    -0.89
    CAP
    -0.84
    amines
    -0.82
     vou
    -0.82
    sted
    -0.81
     Vaugh
    -0.81
    etsy
    -0.78
    oubted
    -0.78
    çīĪ
    -0.77
    POSITIVE LOGITS
    else
    0.95
    endif
    0.85
     ********************************
    0.77
    piece
    0.77
    Else
    0.76
     bidding
    0.76
    Gro
    0.72
     Default
    0.72
    cf
    0.72
    ONSORED
    0.71
    Activations Density 0.911%

    No Known Activations