© 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. 33947
    Prev
    Next
    INDEX
    Explanations

    numerical and textual patterns that involve various names and locations

    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
    496
    +0.11
    0.5%
    314
    +0.09
    0.4%
    163
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.11
    0.08
    659
    +0.09
    0.09
    731
    +0.08
    0.02
    Negative Logits
    posted
    -0.68
    advertisement
    -0.64
    æ©
    -0.62
    taboola
    -0.62
     mot
    -0.61
     abdom
    -0.61
    lde
    -0.60
    Cause
    -0.57
    âĸ¬
    -0.57
    Offline
    -0.55
    POSITIVE LOGITS
    assador
    0.83
    zee
    0.72
    ICAN
    0.70
    culosis
    0.67
    ufact
    0.67
    uku
    0.65
    ixture
    0.64
    arella
    0.64
    oola
    0.64
    amara
    0.61
    Activations Density 14.485%

    No Known Activations