© 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. 1119
    Prev
    Next
    INDEX
    Explanations

    actions related to events or situations involving multiple individuals

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or events related to participation and interaction

    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
    tain
    -0.83
    yond
    -0.73
    been
    -0.72
    obyl
    -0.66
    vp
    -0.66
    cedented
    -0.66
     ..."
    -0.66
    selves
    -0.65
    voy
    -0.65
    LGBT
    -0.64
    POSITIVE LOGITS
     briefly
    0.94
     extensively
    0.85
     however
    0.83
     moreover
    0.80
     accordingly
    0.80
     furthermore
    0.76
     meanwhile
    0.76
     cautiously
    0.76
     plent
    0.75
     immediately
    0.74
    Activations Density 0.605%

    No Known Activations