© 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. 14174
    Prev
    Next
    INDEX
    Explanations

    parts of proper names related to government positions or organizations in Scotland

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or initials, possibly referring to individuals or organizations

    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
    Jer
    -0.94
    iris
    -0.90
     TOR
    -0.89
    ARS
    -0.86
    zar
    -0.85
    TOR
    -0.83
    ars
    -0.81
     138
    -0.81
     ROB
    -0.79
     Jer
    -0.79
    POSITIVE LOGITS
    itt
    0.95
    um
    0.95
     Pence
    0.85
    ums
    0.81
    ess
    0.80
     Dum
    0.80
     Buchanan
    0.80
    odd
    0.79
    ummer
    0.79
    nam
    0.78
    Activations Density 0.317%

    No Known Activations