© 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. 2-RES-JB
    11. 19469
    Prev
    Next
    INDEX
    Explanations

    references to American sports teams and events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams and player dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.79
    skirts
    -0.77
    schild
    -0.75
     vanishing
    -0.71
     censored
    -0.68
    tube
    -0.67
    SPONSORED
    -0.67
     lett
    -0.65
     guiActiveUn
    -0.64
     vill
    -0.64
    POSITIVE LOGITS
     Broncos
    1.03
     Falcons
    1.01
     Bulldogs
    1.00
     Raiders
    0.98
     Tigers
    0.96
     Bears
    0.96
     Oilers
    0.94
     Chiefs
    0.93
     Bengals
    0.93
     Wildcats
    0.92
    Activations Density 0.386%

    No Known Activations