© 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. 8-RES-JB
    11. 20420
    Prev
    Next
    INDEX
    Explanations

    words related to positive emotions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe various qualities or characteristics

    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
    ajor
    -0.85
    Downloadha
    -0.71
     strengthened
    -0.67
     inaug
    -0.67
     corresponding
    -0.67
    authorized
    -0.65
    quart
    -0.63
    supported
    -0.63
    conservancy
    -0.63
    onto
    -0.63
    POSITIVE LOGITS
    ness
    1.25
    ly
    1.13
     Enough
    1.08
    nesses
    1.07
    NESS
    1.00
    est
    0.97
     enough
    0.95
    LY
    0.87
     Bastard
    0.83
    glers
    0.82
    Activations Density 0.218%

    No Known Activations