© 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. 45746
    Prev
    Next
    INDEX
    Explanations

    terms related to auditing and law enforcement positions

    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
    104
    +0.11
    0.6%
    571
    +0.10
    0.5%
    707
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.19
    104
    +0.10
    0.07
    538
    +0.09
    0.05
    Negative Logits
    ells
    -0.59
    eda
    -0.57
    ition
    -0.57
    amping
    -0.56
    er
    -0.55
    ering
    -0.54
    ership
    -0.54
    ugg
    -0.54
     HI
    -0.51
     Kardashian
    -0.51
    POSITIVE LOGITS
     GENERAL
    0.86
     Gadget
    0.86
    general
    0.81
    General
    0.78
    Reviewer
    0.77
     General
    0.74
    iate
    0.73
    ium
    0.72
     Anita
    0.66
    stration
    0.65
    Activations Density 7.997%

    No Known Activations