© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15210
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific event or festival

    oai_token-act-pair · gpt-3.5-turbo

    references to a music festival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worldly
    -0.62
    EStreamFrame
    -0.62
    avez
    -0.61
    cyl
    -0.57
    ################
    -0.57
    fram
    -0.57
    aundering
    -0.55
    llular
    -0.55
    loo
    -0.55
    technical
    -0.54
    POSITIVE LOGITS
    ivals
    1.56
    ivities
    1.22
    Fest
    1.11
     Fest
    1.06
    fest
    1.00
    iversary
    0.92
    aign
    0.85
     festivals
    0.83
    ruary
    0.80
    aceae
    0.80
    Activations Density 0.007%

    No Known Activations