© 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. 16425
    Prev
    Next
    INDEX
    Explanations

    words related to locations or place names

    oai_token-act-pair · gpt-3.5-turbo
    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
    éļ
    -0.82
    OPE
    -0.79
    Privacy
    -0.72
    Autom
    -0.72
    minist
    -0.70
    Reviewed
    -0.69
    apeake
    -0.68
     models
    -0.67
    Customer
    -0.67
    Peace
    -0.67
    POSITIVE LOGITS
    isd
    1.76
    isf
    1.27
    iken
    0.93
     fused
    0.76
    ias
    0.73
     Incarn
    0.71
    lde
    0.71
    stained
    0.69
     Locked
    0.69
    cast
    0.69
    Activations Density 0.001%

    No Known Activations