© 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. 18783
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    repeated auxiliary verbs indicating actions or conditions

    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
    istries
    -0.77
    ificent
    -0.70
    QB
    -0.69
    ifiers
    -0.65
    Words
    -0.64
    ãĥ¯ãĥ³
    -0.63
    Dub
    -0.63
    Bound
    -0.62
     guiActiveUnfocused
    -0.62
    ographs
    -0.61
    POSITIVE LOGITS
     others
    0.86
     countless
    0.85
     many
    0.83
    lihood
    0.82
     any
    0.76
     anyone
    0.75
     other
    0.67
     anybody
    0.65
     ours
    0.64
     dozens
    0.64
    Activations Density 0.054%

    No Known Activations