© 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. 17282
    Prev
    Next
    INDEX
    Explanations

    violent actions or mentions of physical altercations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law enforcement and violence

    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
    ISTORY
    -0.69
    Quantity
    -0.63
    zsche
    -0.60
     renaissance
    -0.59
    breeding
    -0.59
    vi
    -0.59
    cend
    -0.58
     yourselves
    -0.57
     ILCS
    -0.56
    phas
    -0.56
    POSITIVE LOGITS
    selves
    0.78
     inappropriately
    0.78
    soever
    0.77
     itch
    0.76
    itals
    0.75
     goodbye
    0.73
     via
    0.69
     senseless
    0.69
     alike
    0.68
     unconscious
    0.67
    Activations Density 0.773%

    No Known Activations