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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 45341
    Prev
    Next
    INDEX
    Explanations

    recipes for making various food items, such as cakes, bread, yogurt, and tea

    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
    +0.09
    0.9%
    218
    +0.05
    0.5%
    455
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.09
    0.01
    728
    +0.05
    0.04
    59
    +0.04
    0.06
    Negative Logits
     Skies
    -0.32
    burgh
    -0.30
    iberal
    -0.29
    mington
    -0.29
    nesty
    -0.28
    igious
    -0.28
    genre
    -0.28
    views
    -0.28
    2019
    -0.27
    enture
    -0.27
    POSITIVE LOGITS
     sure
    0.44
    grain
    0.35
    otype
    0.35
     batches
    0.35
    ãĥĥãĤ¯
    0.34
    Maker
    0.33
    Kit
    0.33
     makeshift
    0.33
    otypes
    0.33
    éŃĶ
    0.32
    Activations Density 8.009%

    No Known Activations