© 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. 35371
    Prev
    Next
    INDEX
    Explanations

    terms related to agriculture and biotechnology

    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
    182
    +0.09
    0.5%
    314
    +0.08
    0.5%
    288
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.27
    575
    +0.08
    0.16
    709
    +0.08
    0.12
    Negative Logits
    pload
    -0.63
    20439
    -0.59
    ledged
    -0.59
    igan
    -0.54
    psey
    -0.54
    apo
    -0.53
     captcha
    -0.53
    lyak
    -0.53
    fman
    -0.52
    uchin
    -0.51
    POSITIVE LOGITS
     Relations
    0.61
     istg
    0.60
     âĢº
    0.59
    }
    0.56
    istics
    0.55
     Directorate
    0.54
     relations
    0.54
     Architecture
    0.54
     Innovation
    0.54
    Status
    0.54
    Activations Density 8.836%

    No Known Activations