© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45836
    Prev
    Next
    INDEX
    Explanations

    academic and medical research articles related to spinal cord stimulation and health interventions

    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
    95
    +0.13
    0.5%
    316
    +0.11
    0.5%
    625
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.08
    373
    +0.11
    -0.09
    176
    +0.10
    0.05
    Negative Logits
    grounds
    -0.85
    matter
    -0.83
    ÙIJ
    -0.80
    WARE
    -0.74
    Reviewer
    -0.73
    CLASSIFIED
    -0.72
    ãĥ¼ãĤ¯
    -0.72
    tick
    -0.69
    nesday
    -0.69
    buster
    -0.69
    POSITIVE LOGITS
     Zhao
    0.95
     Zhang
    0.94
     et
    0.93
     Peng
    0.84
     Iz
    0.82
     Wang
    0.78
     Liang
    0.77
     Xu
    0.75
     Yan
    0.74
     Qiao
    0.73
    Activations Density 3.646%

    No Known Activations