© 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. 14268
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and technical instructions

    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
    496
    +0.18
    0.7%
    669
    +0.13
    0.5%
    311
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.09
    288
    +0.13
    0.09
    99
    +0.12
    0.06
    Negative Logits
    ifice
    -0.92
    xon
    -0.90
     ç¥ŀ
    -0.88
     TAMADRA
    -0.84
     Machina
    -0.84
    PsyNetMessage
    -0.83
    ahime
    -0.82
    ificial
    -0.82
    ngth
    -0.81
     Bubble
    -0.81
    POSITIVE LOGITS
    mares
    1.35
    ield
    1.13
    ths
    1.13
    bors
    1.07
    teen
    1.05
    mare
    1.01
    IELD
    1.00
    bour
    0.99
    orns
    0.97
    awks
    0.97
    Activations Density 1.210%

    No Known Activations