© 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. 4194
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activity, investigation, and law enforcement

    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%
    126
    +0.12
    0.5%
    7
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.32
    326
    +0.12
    0.27
    343
    +0.10
    0.12
    Negative Logits
    leon
    -0.85
    ando
    -0.85
    mone
    -0.84
    arde
    -0.80
    Thom
    -0.79
    eral
    -0.77
    unal
    -0.75
    opsy
    -0.75
    andr
    -0.74
    xon
    -0.74
    POSITIVE LOGITS
     prevention
    0.75
     hots
    0.75
     concentration
    0.71
     activity
    0.68
     stalking
    0.68
     enthusiasts
    0.67
     susceptibility
    0.66
     density
    0.66
     detection
    0.65
     skeptics
    0.65
    Activations Density 10.926%

    No Known Activations