© 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. 20367
    Prev
    Next
    INDEX
    Explanations

    adjectives or descriptions related to opinions and evaluations

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases that indicate triviality or low seriousness

    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
    onds
    -0.80
    onding
    -0.61
    ioxide
    -0.59
    clerosis
    -0.59
    usalem
    -0.59
     stake
    -0.59
    xit
    -0.58
    asio
    -0.55
     counselor
    -0.55
    OND
    -0.54
    POSITIVE LOGITS
    ingly
    1.01
    istic
    0.98
    istically
    0.97
     compared
    0.95
    ly
    0.95
     sounding
    0.87
     enough
    0.86
     insofar
    0.82
    lly
    0.81
    ified
    0.81
    Activations Density 0.285%

    No Known Activations