© 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. 9-RES-JB
    11. 11282
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a state of being or situation

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating the current state or condition of various subjects

    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
     Removal
    -0.80
     denote
    -0.73
    ints
    -0.73
    oji
    -0.71
     Highlights
    -0.69
    rouse
    -0.68
    odied
    -0.67
     mentions
    -0.67
    bury
    -0.67
    uld
    -0.67
    POSITIVE LOGITS
     littered
    1.06
     rife
    1.02
     evolving
    1.02
     crumbling
    0.99
     riddled
    0.99
     dominated
    0.97
     obsessed
    0.96
     divided
    0.95
     comprised
    0.93
     governed
    0.92
    Activations Density 0.336%

    No Known Activations