© 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. 1-RES-JB
    11. 20970
    Prev
    Next
    INDEX
    Explanations

    words related to physical battering or hitting

    oai_token-act-pair · gpt-3.5-turbo

    words related to the action of hitting or striking in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qual
    -0.88
    egal
    -0.79
    ovo
    -0.74
    flex
    -0.72
     Nevada
    -0.72
    opher
    -0.71
    issue
    -0.67
    rip
    -0.66
    fts
    -0.65
    ported
    -0.64
    POSITIVE LOGITS
     batter
    1.21
     batters
    1.07
    cakes
    1.02
    è¦ļéĨĴ
    0.85
     hitters
    0.82
    halla
    0.82
     encount
    0.81
     cakes
    0.81
    ãĥ¯ãĥ³
    0.78
    cake
    0.77
    Activations Density 0.005%

    No Known Activations