© 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. 0-RES-JB
    11. 6499
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific name or topic, particularly "Stafford."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Stafford" and "Fields."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agine
    -0.72
     obstacle
    -0.69
    ocaly
    -0.68
    atom
    -0.68
     invite
    -0.68
     VO
    -0.67
     synthes
    -0.67
     volleyball
    -0.65
    gey
    -0.64
     Bullet
    -0.63
    POSITIVE LOGITS
     Stafford
    4.01
    Staff
    2.20
     Fields
    1.31
     Hert
    1.19
     Livingston
    1.08
    staff
    1.05
     Bridgewater
    1.02
     Bradford
    1.02
     Petty
    1.00
    Dur
    0.98
    Activations Density 0.041%

    No Known Activations