© 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. 7-RES-JB
    11. 13390
    Prev
    Next
    INDEX
    Explanations

    phrases related to upgrades, exchanges, and transactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating specific relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    press
    -0.81
    Press
    -0.79
    ãĥ©ãĥ³
    -0.78
    wcs
    -0.77
    IP
    -0.76
    OFF
    -0.75
    VID
    -0.71
    Vert
    -0.71
    Leg
    -0.70
    SP
    -0.70
    POSITIVE LOGITS
     a
    0.95
    a
    0.92
     an
    0.77
     another
    0.74
     A
    0.73
     Clyde
    0.66
     atoms
    0.64
     Anne
    0.63
     bartender
    0.63
     antique
    0.62
    Activations Density 0.222%

    No Known Activations