© 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. 13998
    Prev
    Next
    INDEX
    Explanations

    phrases related to holding something or someone accountable

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to accountability

    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
    ibel
    -0.70
    shire
    -0.68
    ————
    -0.68
    naire
    -0.68
    endix
    -0.67
    phrine
    -0.65
    gnu
    -0.64
    ghan
    -0.63
    eger
    -0.62
    atis
    -0.62
    POSITIVE LOGITS
     sway
    1.03
    hold
    1.00
    holder
    0.86
    erness
    0.86
     accountable
    0.86
    overs
    0.84
    holding
    0.83
    holders
    0.82
     hold
    0.80
    fast
    0.79
    Activations Density 0.044%

    No Known Activations