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. 11-RES-JB
    6. 17999
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or records related to sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subt
    -0.61
    use
    -0.58
     Halls
    -0.55
     intercepted
    -0.53
     scrut
    -0.53
     reflections
    -0.53
    wered
    -0.52
    hod
    -0.52
    icus
    -0.52
    actions
    -0.51
    POSITIVE LOGITS
     (.
    0.91
     overall
    0.83
     record
    0.81
    record
    0.74
     Record
    0.69
    iversal
    0.67
     FG
    0.64
    iership
    0.63
    ilogy
    0.63
    BP
    0.63
    Activations Density 0.060%

    No Known Activations