© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14214
    Prev
    Next
    INDEX
    Explanations

    technical terms related to statistical analysis and data interpretation, such as "regression," "predictors," "standard deviations," and "procedures."

    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
    +0.20
    1.3%
    266
    +0.19
    1.3%
    314
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.20
    0.53
    195
    +0.19
    -0.10
    266
    +0.10
    0.64
    Negative Logits
    Dialogue
    -0.56
     payoff
    -0.43
     Ghostbusters
    -0.43
    Laughs
    -0.42
    é¾
    -0.42
     veggies
    -0.42
    calling
    -0.41
     gigs
    -0.41
     whine
    -0.41
     shoved
    -0.41
    POSITIVE LOGITS
     Applicant
    0.54
     ®
    0.51
    ãĥĥãĥĪ
    0.48
    è£ħ
    0.48
    itial
    0.45
    ãĥŃ
    0.45
    trak
    0.44
    ãĥij
    0.43
    ����
    0.42
    atial
    0.42
    Activations Density 59.340%

    No Known Activations