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

    Neuronpedia

    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. 3-RES-JB
    11. 1953
    Prev
    Next
    INDEX
    Explanations

    names of cities, surnames, and flower-related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Bloom" and related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.80
    emet
    -0.79
    ccording
    -0.76
    onut
    -0.73
    ptoms
    -0.72
    etheless
    -0.69
    pez
    -0.69
    ournal
    -0.68
     Indones
    -0.68
    phis
    -0.68
    POSITIVE LOGITS
    field
    1.36
     Bloom
    1.21
    shire
    0.99
    fields
    0.97
    quist
    0.94
    Bloom
    0.93
    gren
    0.89
    endor
    0.89
    FIELD
    0.85
    steen
    0.84
    Activations Density 0.015%

    No Known Activations