© 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. 21793
    Prev
    Next
    INDEX
    Explanations

    descriptions or statements made about a topic

    oai_token-act-pair · gpt-3.5-turbo

    statements and reports regarding allegations and official communications

    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
    acqu
    -0.66
    Plex
    -0.65
    obyl
    -0.62
    pel
    -0.62
     stump
    -0.62
    ardless
    -0.61
    axe
    -0.60
    uncture
    -0.60
     Flavoring
    -0.60
     Maker
    -0.59
    POSITIVE LOGITS
     quoting
    0.79
     adding
    0.73
    thens
    0.68
     omin
    0.67
    iffs
    0.65
     cris
    0.65
     bluntly
    0.64
     titled
    0.61
     convinc
    0.59
     added
    0.59
    Activations Density 0.176%

    No Known Activations