© 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. 40487
    Prev
    Next
    INDEX
    Explanations

    phrases related to daily activities and routines

    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
    +0.17
    0.7%
    651
    +0.14
    0.6%
    267
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.17
    0.07
    651
    +0.14
    0.08
    686
    +0.10
    0.04
    Negative Logits
    holes
    -1.03
    essee
    -0.94
     Gould
    -0.86
    hole
    -0.85
    dinand
    -0.85
    artisan
    -0.84
    OHN
    -0.84
    atchewan
    -0.83
    eer
    -0.81
    aine
    -0.81
    POSITIVE LOGITS
    motion
    1.19
     occurrence
    1.01
     commute
    0.92
     occurrences
    0.91
     servings
    0.88
     necessities
    0.88
     routines
    0.88
     intervals
    0.86
     basis
    0.86
     thereafter
    0.85
    Activations Density 7.697%

    No Known Activations