© 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. 33749
    Prev
    Next
    INDEX
    Explanations

    either isolated words or phrases without a clear common theme

    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
    +0.22
    1.0%
    160
    +0.17
    0.7%
    308
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.22
    0.32
    393
    +0.17
    0.29
    255
    +0.17
    0.15
    Negative Logits
     Lumpur
    -0.81
    eering
    -0.76
     indemn
    -0.74
     nuts
    -0.73
     redress
    -0.72
     oven
    -0.70
     Gaal
    -0.69
     metic
    -0.68
     proced
    -0.67
     palm
    -0.67
    POSITIVE LOGITS
    meaning
    1.24
    which
    1.21
    along
    1.20
    feat
    1.19
    among
    1.19
    advertisement
    1.18
    these
    1.17
    perhaps
    1.17
    that
    1.16
    particularly
    1.16
    Activations Density 14.156%

    No Known Activations