© 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. 4095
    Prev
    Next
    INDEX
    Explanations

    the concept of time and duration mentioned in years

    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
    +0.18
    0.8%
    651
    +0.12
    0.5%
    146
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.18
    0.12
    651
    +0.12
    0.12
    601
    +0.12
    0.07
    Negative Logits
    ople
    -0.84
    ibrary
    -0.79
     contag
    -0.72
    hod
    -0.70
    psey
    -0.69
     Tray
    -0.68
    iqu
    -0.66
    ogly
    -0.64
    ratom
    -0.64
     Halls
    -0.63
    POSITIVE LOGITS
     ago
    1.48
     Ago
    1.23
     olds
    1.01
    long
    1.00
    manship
    0.77
     anniversary
    0.76
    nings
    0.76
     apiece
    0.75
    ns
    0.74
     elapsed
    0.72
    Activations Density 10.062%

    No Known Activations