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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9531
    Prev
    Next
    INDEX
    Explanations

    words related to sports equipment, specifically "ball"

    oai_token-act-pair · gpt-3.5-turbo

    references to voting or ballots

    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
    ä
    -0.74
    akin
    -0.60
    ä½ľ
    -0.60
    Topic
    -0.60
    æĦ
    -0.59
     Eur
    -0.58
    rians
    -0.58
    ä¿
    -0.57
    éĥ
    -0.56
    ITAL
    -0.56
    POSITIVE LOGITS
    ball
    1.52
    balls
    1.20
    Ball
    1.01
    asketball
    0.98
    wagen
    0.97
    park
    0.89
    oon
    0.82
    BALL
    0.82
    oons
    0.81
    istically
    0.80
    Activations Density 0.007%

    No Known Activations