© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5765
    Prev
    Next
    INDEX
    Explanations

    detailed text in a specific language or script

    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
    569
    +0.11
    0.5%
    107
    +0.10
    0.4%
    213
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.02
    48
    +0.10
    0.02
    213
    +0.10
    0.01
    Negative Logits
     Patriarch
    -0.77
    redible
    -0.76
    ovie
    -0.71
    ortium
    -0.69
    essa
    -0.69
     Photograph
    -0.68
    ovych
    -0.67
     Architects
    -0.65
    achev
    -0.64
    ffen
    -0.64
    POSITIVE LOGITS
    à¤
    1.33
    °
    1.28
    «
    1.17
    ®
    1.17
    ļ
    1.15
    ¸
    1.14
    ¨
    1.14
    µ
    1.13
    ¹
    1.13
    ¬
    1.11
    Activations Density 0.133%

    No Known Activations