© 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 EvalsExportsinterp-engineNEWAPI 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. 32445
    Prev
    Next
    INDEX
    Explanations

    words related to data processing and analysis

    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
    +0.25
    1.2%
    288
    +0.17
    0.8%
    271
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.25
    0.45
    138
    +0.17
    0.43
    64
    +0.10
    -0.21
    Negative Logits
    liest
    -0.75
    gets
    -0.66
    legged
    -0.63
    lihood
    -0.63
    sky
    -0.62
    fall
    -0.61
    ortium
    -0.60
    gged
    -0.60
    verty
    -0.59
    uild
    -0.58
    POSITIVE LOGITS
     Processing
    0.88
     processing
    0.86
    utical
    0.76
    folios
    0.73
    nesota
    0.73
    itive
    0.70
     processors
    0.70
    IME
    0.69
    processing
    0.68
     machinery
    0.67
    Activations Density 12.053%

    No Known Activations