© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    code snippets and functions related to 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
    692
    +0.16
    0.5%
    156
    +0.16
    0.5%
    588
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.16
    0.02
    156
    +0.16
    0.02
    132
    +0.14
    0.02
    Negative Logits
    Ü
    -1.29
    spring
    -1.12
    wagen
    -1.06
    arial
    -1.02
    venants
    -1.02
    د
    -0.98
    æ©Ł
    -0.98
    ModLoader
    -0.98
    wright
    -0.97
    BuyableInstoreAndOnline
    -0.97
    POSITIVE LOGITS
     <=
    0.95
     sizeof
    0.91
     NFC
    0.90
     Colts
    0.87
    ==
    0.86
     min
    0.86
     MAX
    0.84
     NETWORK
    0.83
     reached
    0.83
     max
    0.83
    Activations Density 0.150%

    No Known Activations