© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23666
    Prev
    Next
    INDEX
    Explanations

    mentions specific locations in a sports context, particularly related to ice and court

    oai_token-act-pair · gpt-3.5-turbo

    references to sports environments and playing fields

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

    No Comments

    Negative Logits
    xit
    -0.79
    cess
    -0.70
    ĨĴ
    -0.68
     pneum
    -0.67
     Cars
    -0.62
     flavours
    -0.62
     Panzer
    -0.61
    anson
    -0.60
     ICO
    -0.59
    itarian
    -0.59
    POSITIVE LOGITS
    keeper
    0.77
    plays
    0.77
    ographed
    0.76
     announcer
    0.75
     perimeter
    0.75
     scoreboard
    0.74
    yard
    0.74
     ÙĪ
    0.72
     brawl
    0.72
    swing
    0.72
    Activations Density 0.092%

    No Known Activations