© 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. 2-RES-JB
    11. 7458
    Prev
    Next
    INDEX
    Explanations

    positions or stances taken on various topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to a viewpoint or stance on issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STON
    -0.73
    susp
    -0.67
    hemy
    -0.64
    ART
    -0.64
    displayText
    -0.63
    vous
    -0.62
    ignore
    -0.61
     Flavoring
    -0.61
    mph
    -0.60
    vernment
    -0.60
    POSITIVE LOGITS
     position
    1.19
     positions
    1.09
    position
    0.90
    ngth
    0.89
    idon
    0.86
    holders
    0.85
    Position
    0.82
     plank
    0.79
     Position
    0.76
    inctions
    0.75
    Activations Density 0.019%

    No Known Activations