© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 19345
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    IDs related to a specific context or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     merc
    -0.65
     bulb
    -0.62
     Ae
    -0.56
    Initialized
    -0.54
     canal
    -0.54
     cla
    -0.54
     interconnected
    -0.53
     acknow
    -0.53
     DRAG
    -0.53
    È
    -0.52
    POSITIVE LOGITS
    addle
    0.89
    otos
    0.82
    rogram
    0.77
    writers
    0.77
    cheon
    0.76
    punk
    0.75
    walker
    0.75
    rote
    0.75
    kees
    0.73
    cycles
    0.73
    Activations Density 0.070%

    No Known Activations