© 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. 6-RES-JB
    11. 2682
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events, matches, and seasons

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating seasons and games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.80
    umerable
    -0.72
     Canaver
    -0.71
     Cosponsors
    -0.70
     ILCS
    -0.66
    ãĥ¯
    -0.66
    zsche
    -0.65
    helle
    -0.64
    soType
    -0.63
    IUM
    -0.63
    POSITIVE LOGITS
     theirs
    0.79
     scrimmage
    0.75
     playoffs
    0.75
     il
    0.73
     preseason
    0.73
     finals
    0.71
     postseason
    0.70
     Champions
    0.70
     Finals
    0.68
     Playoffs
    0.68
    Activations Density 0.104%

    No Known Activations