© 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. 0-RES-JB
    6. 16946
    Prev
    Next
    INDEX
    Explanations

    references to American football teams, specifically the Chargers and Padres

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the San Diego Chargers football team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hem
    -0.79
     Mog
    -0.78
     anth
    -0.76
     HM
    -0.76
    ¶
    -0.73
     hat
    -0.73
     Norway
    -0.72
     Noah
    -0.71
    yt
    -0.71
     EUR
    -0.70
    POSITIVE LOGITS
     Chargers
    3.61
     Padres
    2.23
    Charg
    1.86
     Clippers
    1.80
     Qualcomm
    1.58
     Charg
    1.58
     Rivers
    1.45
     charger
    1.35
     Raiders
    1.28
     charg
    1.28
    Activations Density 0.026%

    No Known Activations