© 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 Local
    5. 6-RES_SCL-AJT
    6. 39663
    Prev
    Next
    INDEX
    Explanations

    relationships between individuals and their involvement or assistance with various activities or situations

    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
    447
    +0.16
    0.8%
    587
    +0.11
    0.6%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.16
    608
    +0.11
    0.18
    393
    +0.11
    0.19
    Negative Logits
    fighters
    -0.65
    Fed
    -0.65
    agues
    -0.64
    former
    -0.59
    warn
    -0.59
    hari
    -0.58
    Sah
    -0.58
    Champ
    -0.57
    mart
    -0.57
    llah
    -0.57
    POSITIVE LOGITS
     regards
    1.20
     regard
    1.01
    draw
    0.83
    standing
    0.83
    stood
    0.82
     impunity
    0.79
    drawn
    0.78
    holding
    0.76
     respect
    0.72
     propri
    0.71
    Activations Density 4.983%

    No Known Activations