© 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. 2302
    Prev
    Next
    INDEX
    Explanations

    mentions of boys

    oai_token-act-pair · gpt-3.5-turbo

    references to boys and their relationships with girls

    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
    sole
    -0.83
    ointment
    -0.77
    lich
    -0.75
    mediated
    -0.68
    leased
    -0.66
    uncture
    -0.66
    OLOG
    -0.66
    rior
    -0.65
    patient
    -0.65
     Hulk
    -0.64
    POSITIVE LOGITS
    hift
    1.06
     ages
    0.98
    pace
    0.97
    mith
    0.95
    terday
    0.91
    '
    0.88
    hips
    0.86
    ieve
    0.83
    heet
    0.82
    ocial
    0.81
    Activations Density 0.094%

    No Known Activations