© 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. 7-RES-JB
    11. 21809
    Prev
    Next
    INDEX
    Explanations

    sports-related actions and injuries

    oai_token-act-pair · gpt-3.5-turbo

    events or actions related to physical harm or injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.74
     Founders
    -0.72
    atform
    -0.71
     Princ
    -0.71
     Canaver
    -0.70
    esides
    -0.66
     Cosponsors
    -0.64
    erala
    -0.64
     Founding
    -0.63
    inventoryQuantity
    -0.62
    POSITIVE LOGITS
     versa
    0.81
    )).
    0.77
     etc
    0.71
    !".
    0.67
    mark
    0.64
    esque
    0.63
    gently
    0.62
     undet
    0.62
    gren
    0.62
    ido
    0.62
    Activations Density 1.099%

    No Known Activations