© 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. 8-RES-JB
    11. 11847
    Prev
    Next
    INDEX
    Explanations

    verbs indicating an action of leaving or quitting a certain place or position

    oai_token-act-pair · gpt-3.5-turbo

    the infinitive form of verbs expressing actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pring
    -0.69
    grain
    -0.65
    eh
    -0.63
    updated
    -0.63
    Glass
    -0.63
    unn
    -0.63
    Recipe
    -0.62
    enough
    -0.62
    handled
    -0.61
    į
    -0.60
    POSITIVE LOGITS
     pursue
    1.09
     avoid
    1.05
     fend
    1.02
     accommodate
    1.02
     conserve
    0.95
    ilet
    0.94
     explore
    0.94
     appease
    0.92
     join
    0.92
     facilitate
    0.90
    Activations Density 0.213%

    No Known Activations