© 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. 11-RES-JB
    11. 585
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, specifically the Boston Bruins and Boston Celtics

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Boston and its sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.74
    uador
    -0.69
    pter
    -0.69
    loading
    -0.68
    orce
    -0.66
    gypt
    -0.65
    orsche
    -0.65
    olkien
    -0.64
    resses
    -0.64
    aphael
    -0.63
    POSITIVE LOGITS
     Celtics
    1.27
     Bruins
    1.23
     Globe
    1.19
     Dynamics
    1.12
     Marathon
    1.07
     Harbor
    1.05
     Consulting
    1.00
     2024
    0.95
     Garden
    0.92
     College
    0.92
    Activations Density 0.024%

    No Known Activations