© 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. 45748
    Prev
    Next
    INDEX
    Explanations

    news articles related to law enforcement activities and legal matters such as arrests, criminal charges, investigations, and public statements by officials

    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
    527
    +0.12
    0.5%
    73
    +0.11
    0.5%
    712
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    527
    +0.12
    0.05
    640
    +0.11
    0.25
    712
    +0.10
    0.03
    Negative Logits
    iasm
    -0.86
    rawdownloadcloneembedreportprint
    -0.81
    ersen
    -0.71
    phrine
    -0.71
    ãĤ´ãĥ³
    -0.68
    yip
    -0.66
    itely
    -0.66
     gif
    -0.65
    iously
    -0.65
    iday
    -0.63
    POSITIVE LOGITS
    abulary
    0.95
     Deaths
    0.88
     Militia
    0.76
     Authority
    0.75
     Municipal
    0.71
     Enforcement
    0.69
    ento
    0.67
     Association
    0.67
    Common
    0.65
     District
    0.64
    Activations Density 14.725%

    No Known Activations