© 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 Local
    9. 6-RES_SCL-AJT
    11. 32563
    Prev
    Next
    INDEX
    Explanations

    Russian text, potentially related to a particular author or work

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    163
    +0.14
    0.6%
    285
    +0.12
    0.5%
    406
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.12
    406
    +0.12
    0.09
    323
    +0.12
    0.08
    Negative Logits
     contrace
    -0.75
    pmwiki
    -0.74
    isure
    -0.70
     behav
    -0.69
     mathemat
    -0.69
    rero
    -0.68
    scill
    -0.68
    ategory
    -0.67
     compr
    -0.66
     recourse
    -0.65
    POSITIVE LOGITS
    ·
    0.99
    Ñĭ
    0.98
    é¾į
    0.94
    ership
    0.91
    ´
    0.90
    ÏĤ
    0.89
    в
    0.89
    ¦
    0.89
    ±
    0.86
    а
    0.85
    Activations Density 6.137%

    No Known Activations