© 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. 4200
    Prev
    Next
    INDEX
    Explanations

    text related to events happening during the night or in the middle of something

    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
    +0.16
    0.8%
    393
    +0.12
    0.6%
    620
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.16
    0.27
    608
    +0.12
    0.19
    362
    +0.09
    0.14
    Negative Logits
     Cosponsors
    -0.82
    >(
    -0.63
    MSN
    -0.63
    osponsors
    -0.62
     guiIcon
    -0.60
    Reviewer
    -0.60
    ARA
    -0.59
    OY
    -0.58
    apego
    -0.57
    >:
    -0.57
    POSITIVE LOGITS
     nowhere
    0.96
    stad
    0.70
    sight
    0.59
     woods
    0.56
     fray
    0.55
     snowy
    0.54
     Ramadan
    0.54
     furious
    0.54
     Tart
    0.53
     desperation
    0.53
    Activations Density 8.875%

    No Known Activations