© 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. 4-RES-JB
    11. 13230
    Prev
    Next
    INDEX
    Explanations

    mention of the name "idd" followed by either "10" or "9"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Bidd."

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

    No Comments

    Negative Logits
     metast
    -0.77
    pora
    -0.72
    TPP
    -0.69
     tranqu
    -0.66
    xon
    -0.64
    economic
    -0.61
     Bast
    -0.61
    MER
    -0.59
     penetrating
    -0.57
    LOD
    -0.57
    POSITIVE LOGITS
    eenth
    1.04
    idd
    0.93
    leground
    0.92
    lesh
    0.90
    itional
    0.90
    ick
    0.90
    ety
    0.88
    elling
    0.86
    imensional
    0.86
    escription
    0.84
    Activations Density 0.007%

    No Known Activations