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. 0-RES-JB
    6. 89
    Prev
    Next
    INDEX
    Explanations

    terms related to bidding or assessment of value

    oai_token-act-pair · gpt-3.5-turbo

    terms related to food preparation and valuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iment
    -0.95
    iments
    -0.67
    ogo
    -0.65
    Os
    -0.64
    ema
    -0.64
    Victoria
    -0.63
    Christian
    -0.62
    Ul
    -0.62
    Bir
    -0.62
    Ja
    -0.62
    POSITIVE LOGITS
    cooked
    2.03
     Remastered
    1.60
    bid
    1.13
    dash
    1.07
     DX
    0.86
    rish
    0.85
     bridges
    0.71
     Uncharted
    0.69
    valued
    0.69
    complete
    0.68
    Activations Density 0.009%

    No Known Activations