© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33312
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming languages and technology

    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
    645
    +0.13
    0.6%
    314
    +0.13
    0.5%
    525
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.13
    0.09
    291
    +0.13
    0.12
    284
    +0.12
    0.12
    Negative Logits
    wine
    -0.77
    DW
    -0.77
    BBC
    -0.75
    WI
    -0.72
    Marsh
    -0.69
    KK
    -0.67
    NEW
    -0.67
    WOOD
    -0.67
    DX
    -0.67
    RG
    -0.66
    POSITIVE LOGITS
    nant
    0.95
    illance
    0.93
    ascus
    0.92
    monary
    0.86
    cular
    0.82
    asma
    0.80
    itic
    0.80
    emia
    0.80
    iferation
    0.79
    emic
    0.78
    Activations Density 11.670%

    No Known Activations