© 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. 3861
    Prev
    Next
    INDEX
    Explanations

    discussions or interactions between individuals

    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
    218
    +0.03
    0.5%
    679
    +0.02
    0.5%
    493
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.03
    -0.03
    584
    +0.02
    0.10
    399
    +0.02
    0.07
    Negative Logits
    animate
    -0.15
     litter
    -0.14
    ignore
    -0.14
    inner
    -0.13
    arrell
    -0.13
    iddle
    -0.13
    ocks
    -0.13
    helps
    -0.13
    Tile
    -0.12
    cakes
    -0.12
    POSITIVE LOGITS
    ļéĨĴ
    0.19
    nesday
    0.15
     about
    0.14
     detrim
    0.14
    IQ
    0.14
    IUM
    0.13
     Velocity
    0.13
    lich
    0.13
    CLASSIFIED
    0.13
    TD
    0.13
    Activations Density 7.695%

    No Known Activations