© 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 EvalsExportsAPI 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. 11-RES-JB
    11. 14532
    Prev
    Next
    INDEX
    Explanations

    commands or requests intended for action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to journalism and public discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -0.60
     Hits
    -0.57
     ON
    -0.54
     lurking
    -0.53
     onto
    -0.52
     misunderstanding
    -0.50
     failing
    -0.50
     waiting
    -0.50
     departures
    -0.50
     Idle
    -0.50
    POSITIVE LOGITS
    emed
    0.77
    efe
    0.68
    ems
    0.68
    eming
    0.67
    uba
    0.63
    aque
    0.60
    ruff
    0.58
    ribe
    0.57
    velop
    0.55
    ķ
    0.55
    Activations Density 0.475%

    No Known Activations