© 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. 14364
    Prev
    Next
    INDEX
    Explanations

    actions involving physical force or aggression

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "grabbed" 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
    guy
    -0.86
    Ale
    -0.67
    ller
    -0.66
    cas
    -0.66
    study
    -0.65
    die
    -0.64
    resident
    -0.63
    gom
    -0.63
    Reviewer
    -0.61
    cephal
    -0.61
    POSITIVE LOGITS
     onto
    0.85
     grabbed
    0.84
     snatch
    0.78
     grabbing
    0.78
    adobe
    0.76
    EStream
    0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.74
     grab
    0.73
     Pwr
    0.73
    bage
    0.72
    Activations Density 0.011%

    No Known Activations