© 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. 3-RES-JB
    11. 1815
    Prev
    Next
    INDEX
    Explanations

    instances of actions involving cutting off body parts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "cut off."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Export
    -0.71
    hai
    -0.66
    Gall
    -0.65
    MX
    -0.62
    Football
    -0.62
    zilla
    -0.61
    anners
    -0.61
    ĪĴ
    -0.58
    inx
    -0.58
    elsius
    -0.58
    POSITIVE LOGITS
     Broadway
    0.73
    screen
    0.72
    ment
    0.71
    river
    0.68
    shoot
    0.66
    site
    0.66
     leash
    0.66
     dun
    0.65
    cffffcc
    0.65
     shore
    0.64
    Activations Density 0.052%

    No Known Activations