© 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. 4-RES-JB
    11. 22006
    Prev
    Next
    INDEX
    Explanations

    proper nouns that start with "Gall" followed by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Gall."

    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
    BOOK
    -0.82
    terday
    -0.70
    CLASSIFIED
    -0.65
    PRES
    -0.63
    LEASE
    -0.63
     dear
    -0.62
    ccording
    -0.61
     GOLD
    -0.61
     Reloaded
    -0.61
     huh
    -0.61
    POSITIVE LOGITS
    eries
    1.09
    oway
    1.05
    ogly
    1.03
    atin
    1.02
    agher
    1.02
    antry
    0.94
    esian
    0.90
    imore
    0.89
    oise
    0.89
    assed
    0.89
    Activations Density 0.010%

    No Known Activations