© 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. 1-RES-JB
    11. 16443
    Prev
    Next
    INDEX
    Explanations

    mentions of the football team "Titans."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the Tennessee Titans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    renheit
    -0.79
    cery
    -0.75
    ulates
    -0.73
    eme
    -0.73
    gery
    -0.69
    rowth
    -0.68
    selage
    -0.66
    emort
    -0.65
    ificial
    -0.64
    arten
    -0.63
    POSITIVE LOGITS
     Titans
    1.27
    essee
    1.11
    itans
    0.79
    committee
    0.77
    melon
    0.75
     Chattanooga
    0.74
    è¦ļéĨĴ
    0.73
     Tennessee
    0.73
    oshenko
    0.71
     Sapp
    0.71
    Activations Density 0.012%

    No Known Activations