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. 6321
    Prev
    Next
    INDEX
    Explanations

    references to famous individuals or noteworthy figures, particularly those associated with sports or entertainment

    oai_token-act-pair · gpt-3.5-turbo

    references to "star" in the context of prominence or celebrity

    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
    odcast
    -0.81
    channelAvailability
    -0.74
    »Ĵ
    -0.72
     ABE
    -0.70
    iHUD
    -0.70
    Downloadha
    -0.69
     divid
    -0.67
    ascript
    -0.65
    £ı
    -0.63
    Ń·
    -0.62
    POSITIVE LOGITS
    let
    1.16
    lets
    1.13
    bucks
    1.07
    burst
    1.05
    liner
    0.99
    rer
    0.99
    stru
    0.95
     performer
    0.95
    vation
    0.92
     attraction
    0.91
    Activations Density 0.035%

    No Known Activations