© 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. 8-RES-JB
    11. 17180
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or explanation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "That" indicating emphasis or introduction of statements

    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
    ussia
    -0.68
    thro
    -0.67
    cycles
    -0.67
    ãĥ³ãĤ¸
    -0.66
    este
    -0.66
    hips
    -0.65
    perse
    -0.65
    izont
    -0.65
    kamp
    -0.65
    owder
    -0.65
    POSITIVE LOGITS
    cher
    0.97
     begs
    0.83
     sounds
    0.83
     pesky
    0.81
     same
    0.81
     culminated
    0.79
     includes
    0.79
     mattered
    0.78
     translates
    0.78
     fateful
    0.75
    Activations Density 0.128%

    No Known Activations