© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19002
    Prev
    Next
    INDEX
    Explanations

    phrases related to manual actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to manual actions or hand-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     postp
    -0.71
     TT
    -0.63
     Cah
    -0.62
     ambig
    -0.62
    iatus
    -0.61
     reservations
    -0.60
     privately
    -0.60
     rev
    -0.59
    Ń·
    -0.59
     Revenue
    -0.58
    POSITIVE LOGITS
    eye
    1.40
    held
    1.29
    selected
    1.24
    drawn
    1.21
    picked
    1.18
    painted
    1.16
    crafted
    1.10
    written
    1.05
    signed
    1.04
    worn
    1.03
    Activations Density 0.029%

    No Known Activations