© 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. 11-RES-JB
    11. 21296
    Prev
    Next
    INDEX
    Explanations

    information related to contests with winners being chosen

    oai_token-act-pair · gpt-3.5-turbo

    future events or actions that will occur

    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
    quickShipAvailable
    -0.84
    ares
    -0.71
    SpaceEngineers
    -0.69
    luaj
    -0.68
    cffffcc
    -0.67
    Newsletter
    -0.65
    ebus
    -0.64
    ecause
    -0.64
    soType
    -0.63
     Hits
    -0.61
    POSITIVE LOGITS
     be
    1.29
     receive
    1.07
     determine
    1.01
     consist
    1.01
     remain
    0.97
     vary
    0.95
     comprise
    0.95
     also
    0.94
     NOT
    0.94
     notify
    0.92
    Activations Density 0.127%

    No Known Activations