© 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. 11-RES-JB
    11. 18769
    Prev
    Next
    INDEX
    Explanations

    questions being asked in interviews or surveys

    oai_token-act-pair · gpt-3.5-turbo

    instances of questions or inquiries made during interviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fit
    -0.67
    gradation
    -0.60
    jam
    -0.59
    Torrent
    -0.58
    AMY
    -0.57
     conflic
    -0.57
    MpServer
    -0.56
    Made
    -0.55
    yond
    -0.54
    UCT
    -0.52
    POSITIVE LOGITS
     whether
    1.30
     why
    1.21
     if
    1.08
     about
    1.04
     how
    0.98
    whether
    0.95
     rhet
    0.95
     what
    0.93
     aloud
    0.90
     bluntly
    0.87
    Activations Density 0.048%

    No Known Activations