© 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. 3-RES-JB
    11. 10726
    Prev
    Next
    INDEX
    Explanations

    phrases related to second-place finishes or competitions related to running

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "runner" and "runners" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olia
    -0.82
    ropy
    -0.76
    ornia
    -0.73
    oral
    -0.70
    inian
    -0.68
    orically
    -0.68
    inatory
    -0.68
    elsius
    -0.67
    rification
    -0.66
    orical
    -0.66
    POSITIVE LOGITS
    ners
    1.01
     runner
    0.93
    bridge
    0.91
     Runner
    0.90
    swick
    0.87
    ways
    0.86
     runners
    0.85
    wear
    0.83
    runner
    0.81
    knit
    0.79
    Activations Density 0.013%

    No Known Activations