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. 9-RES-JB
    6. 339
    Prev
    Next
    INDEX
    Explanations

    numerical records and achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to records and record-breaking achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    incinn
    -0.75
    mop
    -0.69
    rily
    -0.65
    dot
    -0.65
    markets
    -0.64
    sov
    -0.63
    bane
    -0.63
    flex
    -0.63
     tox
    -0.63
     pand
    -0.63
    POSITIVE LOGITS
     holder
    0.96
     breaker
    0.80
     scorer
    0.79
    keeping
    0.79
     record
    0.78
    keeper
    0.76
     Record
    0.75
    breaking
    0.74
     Holder
    0.74
     Breaker
    0.74
    Activations Density 0.072%

    No Known Activations