© 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. 0-RES-JB
    11. 1063
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "SB" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to specific legislative bills and their designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onne
    -0.77
    oeuv
    -0.75
     cent
    -0.69
    ale
    -0.67
     explorers
    -0.65
     pies
    -0.63
    rene
    -0.63
     Trave
    -0.62
     linen
    -0.62
     pie
    -0.61
    POSITIVE LOGITS
     SB
    4.05
    SB
    2.74
     HB
    1.92
    HB
    1.49
     HR
    1.35
     AB
    1.34
     RB
    1.32
    sb
    1.21
     SAP
    1.21
     BB
    1.20
    Activations Density 0.017%

    No Known Activations