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. 19738
    Prev
    Next
    INDEX
    Explanations

    references to an online platform

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "spring" in various contexts

    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
    ional
    -0.65
     protracted
    -0.64
    fleet
    -0.64
     lending
    -0.63
     rapport
    -0.62
    rum
    -0.62
    llan
    -0.61
     Lumpur
    -0.61
     sighting
    -0.60
     locality
    -0.59
    POSITIVE LOGITS
    iage
    0.83
     Chero
    0.82
    ignt
    0.76
    ieve
    0.70
     Under
    0.68
     CTR
    0.67
    iple
    0.67
     Siber
    0.66
     under
    0.66
     Reborn
    0.66
    Activations Density 0.000%

    No Known Activations