© 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. 1-RES-JB
    11. 22854
    Prev
    Next
    INDEX
    Explanations

    references to baseball-related terminology, particularly focusing on actions related to the catcher around the plate

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "plate" in various contexts, primarily related to sports or physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.83
     Aud
    -0.82
    PRES
    -0.73
    vernment
    -0.72
     Word
    -0.71
    nie
    -0.69
    emouth
    -0.69
     Winston
    -0.67
    ellig
    -0.67
    ijah
    -0.66
    POSITIVE LOGITS
     plate
    1.38
    plate
    1.28
     plates
    1.15
     Plate
    1.00
    plates
    0.83
     lamps
    0.82
     armour
    0.78
    washer
    0.78
    cloth
    0.77
    meal
    0.77
    Activations Density 0.007%

    No Known Activations