© 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. 32888
    Prev
    Next
    INDEX
    Explanations

    technical terms related to military operations and equipment

    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
    +0.25
    1.1%
    481
    +0.19
    0.9%
    565
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.25
    0.40
    326
    +0.19
    0.36
    481
    +0.12
    0.34
    Negative Logits
     Citiz
    -0.77
     contrace
    -0.77
     proble
    -0.74
     intimid
    -0.72
    د
    -0.70
     assum
    -0.69
     princ
    -0.69
     treasury
    -0.69
     charism
    -0.68
     bible
    -0.68
    POSITIVE LOGITS
    xt
    0.77
    nos
    0.77
    adium
    0.76
    anth
    0.74
    aro
    0.74
    hess
    0.73
    mt
    0.73
    dylib
    0.72
    alli
    0.70
    llan
    0.69
    Activations Density 20.701%

    No Known Activations