© 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. 2-RES-JB
    11. 19433
    Prev
    Next
    INDEX
    Explanations

    references to the sports team "Heat."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the sports team "Heat."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arge
    -0.72
    VICE
    -0.71
     Mond
    -0.71
    alia
    -0.66
    roup
    -0.65
    ystem
    -0.65
    ication
    -0.64
    ledged
    -0.64
    ablishment
    -0.63
     Rockefeller
    -0.61
    POSITIVE LOGITS
     Heat
    1.22
    Heat
    1.14
     ILCS
    1.03
    hens
    1.00
    waves
    0.89
    seekers
    0.85
    heat
    0.82
     Seasons
    0.79
     exch
    0.76
    wave
    0.75
    Activations Density 0.005%

    No Known Activations