Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45391
    Prev
    Next
    INDEX
    Explanations

    names and mentions of medical procedures

    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
    190
    +0.10
    0.5%
    549
    +0.10
    0.5%
    579
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.21
    709
    +0.10
    0.11
    288
    +0.10
    0.19
    Negative Logits
    ODUCT
    -0.64
    oubted
    -0.61
    ogue
    -0.61
    oting
    -0.58
    ship
    -0.58
     chrom
    -0.56
    istically
    -0.55
    ISH
    -0.55
     Arist
    -0.54
    IFIED
    -0.53
    POSITIVE LOGITS
    lla
    0.86
    phrine
    0.84
    tto
    0.81
    rette
    0.78
    tta
    0.76
    lli
    0.75
    utic
    0.74
    lett
    0.72
    xia
    0.71
    tti
    0.70
    Activations Density 7.670%

    No Known Activations