© 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. 4064
    Prev
    Next
    INDEX
    Explanations

    phrases related to reactions or responses to various situations or events

    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
    +0.21
    0.9%
    749
    +0.14
    0.6%
    709
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    749
    +0.21
    0.07
    23
    +0.14
    0.08
    259
    +0.12
    0.05
    Negative Logits
    holder
    -0.79
    iciency
    -0.76
    hold
    -0.74
    locked
    -0.71
    fficiency
    -0.66
     Sinai
    -0.66
    inav
    -0.64
     Sustainable
    -0.63
    scribe
    -0.63
    holding
    -0.62
    POSITIVE LOGITS
    ivated
    1.33
    ivation
    1.20
    ivating
    1.17
    aries
    1.13
     reaction
    1.12
     reactions
    1.10
     Reaction
    0.99
    iv
    0.87
     negatively
    0.86
    ivity
    0.85
    Activations Density 8.251%

    No Known Activations