© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32376
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming structures and legal documents

    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
    +0.23
    1.0%
    336
    +0.11
    0.5%
    509
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.23
    0.06
    325
    +0.11
    0.07
    336
    +0.11
    0.04
    Negative Logits
    ãĤ©
    -0.94
    vae
    -0.80
    rolet
    -0.79
     Miliband
    -0.79
    lehem
    -0.78
    ãĥ©
    -0.76
    SG
    -0.75
     Nadu
    -0.75
    rities
    -0.74
    peria
    -0.74
    POSITIVE LOGITS
    lies
    1.47
    liness
    1.16
    etary
    1.00
    eous
    0.92
    ylum
    0.89
    uria
    0.84
    books
    0.82
    cy
    0.81
    able
    0.80
    ership
    0.79
    Activations Density 6.414%

    No Known Activations