© 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. 34796
    Prev
    Next
    INDEX
    Explanations

    references to legal or criminal justice settings and actions

    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
    481
    +0.04
    0.7%
    459
    +0.03
    0.6%
    501
    +0.03
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.04
    0.05
    10
    +0.03
    0.06
    501
    +0.03
    0.07
    Negative Logits
     plurality
    -0.17
    witz
    -0.16
     vul
    -0.15
     Nex
    -0.15
     puzz
    -0.15
     Phill
    -0.15
     validity
    -0.15
     Ranch
    -0.14
    semble
    -0.14
    thora
    -0.14
    POSITIVE LOGITS
    ictions
    0.17
     indefinitely
    0.17
    avorite
    0.16
    agy
    0.16
    âĢİ
    0.16
    artifacts
    0.16
    Aid
    0.15
    fighting
    0.15
    enary
    0.15
    meyer
    0.15
    Activations Density 4.709%

    No Known Activations