© 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. 17271
    Prev
    Next
    INDEX
    Explanations

    forms of phenomena or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to different types or categories

    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
     Hots
    -0.63
     VIDEOS
    -0.63
    bley
    -0.62
     Watching
    -0.62
    ĸļ
    -0.61
    ghan
    -0.61
    iets
    -0.60
     Wand
    -0.59
     Ammo
    -0.58
     bark
    -0.58
    POSITIVE LOGITS
    aldehyde
    1.44
    idable
    1.17
    ative
    1.09
    atter
    1.01
    ality
    0.97
    atted
    0.95
    ulating
    0.95
    ulas
    0.93
    ul
    0.93
    ula
    0.91
    Activations Density 0.024%

    No Known Activations