© 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. 7-RES-JB
    11. 13518
    Prev
    Next
    INDEX
    Explanations

    things related to physical locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical references or measurements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owship
    -0.59
     uncond
    -0.55
     withd
    -0.54
    orsi
    -0.52
    abwe
    -0.52
     mosqu
    -0.52
    inez
    -0.51
    ascus
    -0.51
    rongh
    -0.51
    Islamic
    -0.51
    POSITIVE LOGITS
     airs
    0.66
     aside
    0.66
     hindsight
    0.62
    ?)
    0.61
     trivia
    0.59
     disclaimer
    0.59
     caveat
    0.57
     nods
    0.56
     wise
    0.54
     irony
    0.54
    Activations Density 1.681%

    No Known Activations