© 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. 23027
    Prev
    Next
    INDEX
    Explanations

    keywords related to the name "Earlham"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ham"

    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
    UCT
    -0.74
    enhagen
    -0.70
    ahead
    -0.67
    ãĥ´
    -0.64
    REDACTED
    -0.62
    PLAY
    -0.61
    ATING
    -0.61
    LCS
    -0.60
     diffusion
    -0.60
    KI
    -0.60
    POSITIVE LOGITS
    pton
    1.52
    ilton
    1.27
    mers
    1.12
    sburg
    1.11
    monds
    1.10
    mond
    1.07
    ming
    0.98
    shire
    0.94
    bra
    0.93
    enei
    0.93
    Activations Density 0.021%

    No Known Activations