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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12043
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical measures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to counts or endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibur
    -0.75
    conom
    -0.68
    uv
    -0.66
    bite
    -0.63
     fumes
    -0.59
     electricity
    -0.57
     electrical
    -0.56
     flares
    -0.56
     damaged
    -0.55
    oward
    -0.55
    POSITIVE LOGITS
     numbering
    1.20
     list
    1.16
     Ranking
    1.09
     grouping
    1.07
     Lists
    1.07
     alphabet
    1.04
     ranking
    1.03
     lists
    1.01
     counting
    0.98
     rankings
    0.98
    Activations Density 1.269%

    No Known Activations