© 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. 1-RES-JB
    11. 16840
    Prev
    Next
    INDEX
    Explanations

    references to the city of Raqqa

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Raqqa

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UM
    -0.77
     Scotch
    -0.75
    enez
    -0.75
    PASS
    -0.73
    FACE
    -0.73
     CFR
    -0.72
     Britann
    -0.72
    enegger
    -0.69
     Zoom
    -0.69
     ADA
    -0.69
    POSITIVE LOGITS
     Raqqa
    1.18
    qqa
    1.07
     rall
    1.04
    ²¾
    0.88
    ©¶æ¥µ
    0.86
     caliphate
    0.81
    ignt
    0.75
     Idlib
    0.74
     Jinping
    0.73
    \\\\\\\\\\\\\\\\
    0.72
    Activations Density 0.009%

    No Known Activations