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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35750
    Prev
    Next
    INDEX
    Explanations

    details related to personal experiences and emotional moments in various situations

    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
    1.3%
    566
    +0.19
    1.0%
    393
    +0.19
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.25
    0.20
    55
    +0.19
    0.20
    14
    +0.19
    0.10
    Negative Logits
     entails
    -0.66
     Highlands
    -0.64
     Highlights
    -0.63
     Extend
    -0.63
    ESE
    -0.60
     Users
    -0.59
     Which
    -0.58
    guy
    -0.58
     comprises
    -0.58
     Current
    -0.58
    POSITIVE LOGITS
     able
    1.07
     supposed
    0.99
    nt
    0.97
     afraid
    0.96
     unable
    0.95
     glad
    0.95
     fortunate
    0.94
     lucky
    0.93
     expecting
    0.93
     gonna
    0.93
    Activations Density 10.742%

    No Known Activations