© 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 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12772
    Prev
    Next
    INDEX
    Explanations

    instances of the word "just" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    498
    +0.17
    0.6%
    457
    +0.12
    0.4%
    393
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.17
    0.08
    744
    +0.12
    0.08
    633
    +0.12
    0.07
    Negative Logits
    senal
    -0.92
    glomer
    -0.86
    luster
    -0.84
    existent
    -0.82
    interstitial
    -0.82
    externalActionCode
    -0.82
     Hydra
    -0.81
    definition
    -0.80
    ixel
    -0.79
    lav
    -0.78
    POSITIVE LOGITS
    ifiable
    1.35
    ifications
    1.34
     kidding
    1.21
    ices
    1.18
    ifi
    1.17
    ified
    1.13
    itia
    1.11
     FY
    1.10
    if
    1.08
    ification
    1.07
    Activations Density 0.694%

    No Known Activations