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. 3-RES-JB
    6. 13909
    Prev
    Next
    INDEX
    Explanations

    references to scholarly titles or designations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academic achievement and scholarship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cakes
    -0.78
     rigs
    -0.78
    stones
    -0.74
    bread
    -0.69
    fits
    -0.68
    reb
    -0.67
    nuts
    -0.65
     installations
    -0.65
     bonuses
    -0.65
     tweaks
    -0.64
    POSITIVE LOGITS
     Scholar
    1.05
     Medline
    0.99
     Crossref
    0.97
    ibli
    0.94
     citation
    0.93
    lished
    0.92
    ibrary
    0.91
     Journals
    0.89
     CrossRef
    0.87
    umbn
    0.82
    Activations Density 0.034%

    No Known Activations