© 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. 3-RES-JB
    11. 11395
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports teams, primarily focusing on the team named "Bengals" and the individual named "Dalton"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and teams, particularly the names Dalton and Bengals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.87
    ieth
    -0.86
    sburg
    -0.84
     Aires
    -0.81
     McKay
    -0.74
    lé
    -0.70
    åº
    -0.70
    ledge
    -0.70
    arer
    -0.70
     Zub
    -0.69
    POSITIVE LOGITS
    opter
    0.74
    CVE
    0.71
    cone
    0.69
     mol
    0.69
     mitigation
    0.65
    ŃĶ
    0.64
    interstitial
    0.62
    seq
    0.61
     [|
    0.61
    hole
    0.61
    Activations Density 0.015%

    No Known Activations