© 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. 10-RES-JB
    11. 8072
    Prev
    Next
    INDEX
    Explanations

    sporting event matchups

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of "vs" indicating competition or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.80
    estern
    -0.67
     sensit
    -0.61
     ancest
    -0.61
     furnish
    -0.60
     evenings
    -0.59
     moreover
    -0.59
     liner
    -0.59
    DragonMagazine
    -0.58
     crossings
    -0.58
    POSITIVE LOGITS
    .,
    1.21
    .;
    1.06
    .:
    0.99
    .-
    0.99
    .?
    0.92
    ./
    0.83
    ._
    0.82
    .),
    0.81
    .
    0.81
    .,"
    0.79
    Activations Density 0.021%

    No Known Activations