© 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. 10-RES-JB
    11. 2629
    Prev
    Next
    INDEX
    Explanations

    announcements or statements made in a formal setting or official context

    oai_token-act-pair · gpt-3.5-turbo

    announcements regarding meetings and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     effortlessly
    -0.72
     flourished
    -0.69
     realised
    -0.66
     brilliantly
    -0.64
     warped
    -0.64
     Recession
    -0.64
    iuses
    -0.63
     perfection
    -0.61
     perished
    -0.61
    hett
    -0.60
    POSITIVE LOGITS
     tomorrow
    1.45
     next
    1.12
    Tuesday
    0.98
    Wednesday
    0.97
    Thursday
    0.97
     Thursday
    0.95
    morrow
    0.93
    soDeliveryDate
    0.92
     Wednesday
    0.92
     Tues
    0.90
    Activations Density 0.363%

    No Known Activations