© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21084
    Prev
    Next
    INDEX
    Explanations

    mentions of weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to weapons

    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
    pace
    -0.92
    weet
    -0.77
    leep
    -0.73
    cess
    -0.71
    ilver
    -0.70
    aways
    -0.67
    gres
    -0.67
    agascar
    -0.67
    hu
    -0.65
    borough
    -0.65
    POSITIVE LOGITS
    ized
    1.09
    ised
    1.07
    ry
    1.06
    izes
    1.05
    izer
    1.02
    ization
    0.98
    izations
    0.93
    iser
    0.91
    ises
    0.91
    isation
    0.89
    Activations Density 0.052%

    No Known Activations