© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4664
    Prev
    Next
    INDEX
    Explanations

    specific statements indicating a definitive period of time or duration

    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
    0.7%
    218
    +0.15
    0.6%
    450
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.16
    0.12
    388
    +0.15
    0.07
    731
    +0.12
    0.02
    Negative Logits
    raid
    -0.86
    eas
    -0.76
    puff
    -0.75
    Desc
    -0.71
    çīĪ
    -0.71
    jac
    -0.70
    certain
    -0.70
    cigarette
    -0.70
    venture
    -0.70
    ek
    -0.69
    POSITIVE LOGITS
    soever
    0.82
     adulthood
    0.79
    terday
    0.78
     proven
    0.72
    pite
    0.71
    itures
    0.70
    atcher
    0.69
     AFTER
    0.69
    iversal
    0.69
     midnight
    0.68
    Activations Density 8.423%

    No Known Activations