© 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. 13312
    Prev
    Next
    INDEX
    Explanations

    phrases related to sharing information, news, or updates

    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
    481
    +0.14
    0.5%
    203
    +0.14
    0.5%
    246
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.14
    0.01
    134
    +0.14
    0.01
    373
    +0.13
    0.00
    Negative Logits
    REF
    -0.89
    rians
    -0.88
    IAN
    -0.81
     Dictionary
    -0.80
    CHA
    -0.80
     covari
    -0.78
     Lisp
    -0.76
    RW
    -0.75
    Capt
    -0.75
    JSON
    -0.74
    POSITIVE LOGITS
    oak
    0.98
    apor
    0.95
    ãĤ¡
    0.92
    xual
    0.91
    bugs
    0.90
    bug
    0.89
    utic
    0.87
    kamp
    0.84
    uci
    0.84
    ups
    0.83
    Activations Density 0.000%

    No Known Activations