© 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. 3829
    Prev
    Next
    INDEX
    Explanations

    references to events or incidents related to stunts or similar activities

    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
    151
    +0.10
    0.6%
    270
    +0.09
    0.6%
    644
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.24
    326
    +0.09
    0.23
    709
    +0.09
    0.14
    Negative Logits
    cin
    -0.65
    ocol
    -0.63
    usable
    -0.59
    ice
    -0.59
    ighting
    -0.58
     Fah
    -0.57
    istic
    -0.57
    iasco
    -0.55
    azes
    -0.53
    ãĥ³ãĤ¸
    -0.53
    POSITIVE LOGITS
    UAL
    0.70
    liga
    0.59
    CRIP
    0.59
     Avenger
    0.57
    woman
    0.55
    uality
    0.55
    men
    0.54
    lift
    0.54
    ARDIS
    0.53
    crew
    0.52
    Activations Density 8.088%

    No Known Activations