© 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. 23479
    Prev
    Next
    INDEX
    Explanations

    mentions of physical objects

    oai_token-act-pair · gpt-3.5-turbo

    references to competition or challenges

    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
     Jagu
    -0.75
    assies
    -0.75
    Ire
    -0.71
     Oval
    -0.71
     helicop
    -0.65
    bledon
    -0.64
    DAQ
    -0.63
    elines
    -0.63
    Champ
    -0.59
     cabinets
    -0.59
    POSITIVE LOGITS
     ·
    0.71
     ..........
    0.63
    cop
    0.61
     Registered
    0.60
    immer
    0.59
    irl
    0.58
     variant
    0.57
     Member
    0.57
     illustration
    0.56
     investigator
    0.56
    Activations Density 0.197%

    No Known Activations