© 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. 21316
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters, likely from the Russian language

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Marsha" and related forms

    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
    ees
    -0.66
    shire
    -0.66
    ered
    -0.63
    eals
    -0.62
     duct
    -0.60
    worthy
    -0.60
     Foley
    -0.59
    ISA
    -0.59
     Minotaur
    -0.58
     bour
    -0.58
    POSITIVE LOGITS
    abulary
    1.01
    mallow
    0.98
    batch
    0.90
    ote
    0.80
    ²¾
    0.79
    ãĥĨãĤ£
    0.75
    acular
    0.73
    ãĥ´ãĤ¡
    0.73
    kus
    0.72
    atom
    0.71
    Activations Density 0.044%

    No Known Activations