© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 3406
    Prev
    Next
    INDEX
    Explanations

    references to the city "Buffalo" and its associated sports teams

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Buffalo" and its related entities, particularly sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ially
    -0.87
    olation
    -0.80
    egal
    -0.77
    olate
    -0.73
    arial
    -0.73
    acly
    -0.71
    olated
    -0.71
    ace
    -0.70
    ICES
    -0.69
    enemy
    -0.68
    POSITIVE LOGITS
     Trace
    1.09
     Niagara
    1.08
     Sabres
    1.06
     Bills
    1.00
    ¥ŀ
    0.79
     Springfield
    0.78
     Knife
    0.75
    urst
    0.72
    town
    0.71
     Beaut
    0.71
    Activations Density 0.036%

    No Known Activations