© 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. 40805
    Prev
    Next
    INDEX
    Explanations

    instances and comparisons of quantities and measurements, especially related to physical objects or conditions

    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
    320
    +0.14
    0.7%
    331
    +0.12
    0.6%
    132
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.14
    0.03
    331
    +0.12
    0.09
    178
    +0.11
    0.13
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.70
    MAP
    -0.69
    ayne
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
    é¾
    -0.59
     showc
    -0.57
    imeters
    -0.55
     annotations
    -0.54
    DERR
    -0.54
     SHARES
    -0.52
    POSITIVE LOGITS
     much
    0.87
    oooo
    0.81
    oths
    0.80
    zin
    0.78
    aked
    0.77
     anymore
    0.76
    ppy
    0.75
     far
    0.73
    apy
    0.71
    oooooooo
    0.70
    Activations Density 5.318%

    No Known Activations