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. 10717
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a desire or request

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intent

    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
     correct
    -0.69
     forth
    -0.65
     reg
    -0.64
     seals
    -0.63
     fragments
    -0.63
     consistent
    -0.63
     borne
    -0.63
     hy
    -0.62
     stag
    -0.62
     propag
    -0.62
    POSITIVE LOGITS
    Want
    3.11
     Want
    3.11
    want
    1.68
     WANT
    1.56
     Need
    1.33
    Interested
    1.25
     Wanted
    1.25
    Need
    1.16
     want
    1.11
     Feel
    1.11
    Activations Density 0.013%

    No Known Activations