© 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. 40331
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data error handling or software bug tracking

    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
    +0.25
    1.1%
    361
    +0.10
    0.4%
    157
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.25
    -0.01
    608
    +0.10
    0.19
    276
    +0.10
    0.15
    Negative Logits
     Beetle
    -0.70
     Tsukuyomi
    -0.67
     Soup
    -0.65
     whoever
    -0.65
     Ages
    -0.64
    anus
    -0.63
    Hide
    -0.63
     Agric
    -0.62
    isine
    -0.62
     Administ
    -0.61
    POSITIVE LOGITS
     noteworthy
    0.98
     factor
    0.92
     notable
    0.91
     important
    0.86
     aspect
    0.81
    details
    0.81
     bombshell
    0.80
    factor
    0.80
     factors
    0.80
     troubling
    0.79
    Activations Density 14.619%

    No Known Activations