© 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. 8-RES-JB
    11. 3373
    Prev
    Next
    INDEX
    Explanations

    instances of self-affirmation and demonstrating competence or worthiness

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and references to individual identity

    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
     retrieval
    -0.66
    uld
    -0.64
    UM
    -0.60
     Medline
    -0.60
    arton
    -0.59
    panel
    -0.59
    rouse
    -0.58
     winds
    -0.58
     Torrent
    -0.58
    mentioned
    -0.58
    POSITIVE LOGITS
     exist
    0.83
     AUTH
    0.75
     superiority
    0.74
     trustworthy
    0.73
     authentic
    0.72
    ãģĻ
    0.70
     worthy
    0.70
     exists
    0.69
    chwitz
    0.69
     cares
    0.69
    Activations Density 0.384%

    No Known Activations