© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12655
    Prev
    Next
    INDEX
    Explanations

    mentions of personal accounts or life stories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to memoirs and autobiographies

    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
    upid
    -0.75
    inence
    -0.71
    enhagen
    -0.71
    OPA
    -0.69
    regulated
    -0.68
    bledon
    -0.68
    paren
    -0.64
     unregulated
    -0.61
    ulic
    -0.61
    holes
    -0.60
    POSITIVE LOGITS
     Chapters
    1.04
     memoir
    1.02
     narr
    0.94
     narrated
    0.93
     recounted
    0.90
     chron
    0.90
     recounts
    0.86
     chapters
    0.84
     anthology
    0.84
     tales
    0.83
    Activations Density 0.101%

    No Known Activations