© 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. 7-RES-JB
    11. 18004
    Prev
    Next
    INDEX
    Explanations

    prominent or important figures in various contexts or fields

    oai_token-act-pair · gpt-3.5-turbo

    references to influential or prominent individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anium
    -0.70
    okemon
    -0.67
    apons
    -0.63
     Horses
    -0.63
    elligence
    -0.61
    assic
    -0.59
     Ples
    -0.58
    ilation
    -0.58
     worms
    -0.56
     cerv
    -0.56
    POSITIVE LOGITS
    aces
    0.81
    aced
    0.80
     influ
    0.75
     endors
    0.75
    lier
    0.75
    cci
    0.74
    acing
    0.74
     onstage
    0.73
     Flavoring
    0.72
    rities
    0.71
    Activations Density 0.145%

    No Known Activations