© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 540
    Prev
    Next
    INDEX
    Explanations

    terms indicating disagreement or conflict between different parties or entities

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating conflict or opposition

    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
    aceutical
    -0.76
    FTWARE
    -0.59
    planes
    -0.57
    QL
    -0.56
    Ts
    -0.56
    SHIP
    -0.56
     thereof
    -0.55
    uay
    -0.54
    cert
    -0.54
    HTTP
    -0.54
    POSITIVE LOGITS
     least
    1.25
    yp
    1.08
     odds
    0.99
     logger
    0.97
     pains
    0.93
    onement
    0.93
    roph
    0.91
    oned
    0.86
     risk
    0.86
     liberty
    0.86
    Activations Density 0.090%

    No Known Activations