© 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. 33136
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical recovery and rehabilitation

    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
    +0.29
    1.4%
    288
    +0.17
    0.8%
    575
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.29
    0.14
    640
    +0.17
    0.22
    385
    +0.10
    0.14
    Negative Logits
    OPA
    -0.76
    nic
    -0.71
    chery
    -0.70
    ãĤ°
    -0.65
    sky
    -0.64
    à¨
    -0.64
    VP
    -0.64
    pol
    -0.63
    âĸ¬âĸ¬
    -0.61
    abad
    -0.61
    POSITIVE LOGITS
    overy
    0.76
    ees
    0.73
     recover
    0.72
    ilitating
    0.72
     recovery
    0.71
     recovering
    0.67
     recovers
    0.67
    algia
    0.67
    iets
    0.64
     recovered
    0.63
    Activations Density 11.181%

    No Known Activations