© 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. 35009
    Prev
    Next
    INDEX
    Explanations

    video links

    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
    488
    +0.13
    0.6%
    497
    +0.13
    0.6%
    587
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.03
    154
    +0.13
    0.14
    731
    +0.11
    0.05
    Negative Logits
     Levant
    -1.03
     scrut
    -0.67
     coord
    -0.66
    Phones
    -0.62
     transf
    -0.61
     MFT
    -0.61
     impetus
    -0.61
     confines
    -0.61
     Redux
    -0.60
    leans
    -0.59
    POSITIVE LOGITS
    xus
    0.82
    oa
    0.79
    bj
    0.78
    bi
    0.76
    boa
    0.76
    anu
    0.75
    gp
    0.74
    mb
    0.73
    rice
    0.71
    kef
    0.71
    Activations Density 10.822%

    No Known Activations