© 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. 40418
    Prev
    Next
    INDEX
    Explanations

    details about traffic violations and legal issues related to them

    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
    +0.28
    1.4%
    500
    +0.10
    0.5%
    170
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.28
    0.18
    288
    +0.10
    0.27
    500
    +0.10
    0.15
    Negative Logits
    properties
    -0.65
     reservoirs
    -0.63
     sexes
    -0.58
     sights
    -0.58
    amina
    -0.57
     Sections
    -0.56
    hedral
    -0.55
    eworks
    -0.55
     warehouses
    -0.55
     buildings
    -0.54
    POSITIVE LOGITS
     involving
    0.81
    breaker
    0.73
    athon
    0.73
    able
    0.70
     uttered
    0.68
     ..........
    0.64
    .–
    0.61
     attempt
    0.60
     whiff
    0.60
    ="/
    0.59
    Activations Density 10.732%

    No Known Activations