© 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. 9-RES-JB
    11. 16594
    Prev
    Next
    INDEX
    Explanations

    phrases describing physical actions with force or intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing physical force or destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Industries
    -0.70
    pton
    -0.70
    itially
    -0.66
    bridge
    -0.66
     SECTION
    -0.65
    lio
    -0.65
    emies
    -0.65
     Dise
    -0.62
    EMBER
    -0.62
    obook
    -0.61
    POSITIVE LOGITS
     impunity
    1.78
     ease
    1.49
    stood
    1.27
    draw
    1.23
    drawn
    1.13
     abandon
    1.10
    standing
    1.09
     gust
    1.08
     dignity
    1.04
     regard
    1.00
    Activations Density 0.150%

    No Known Activations