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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20845
    Prev
    Next
    INDEX
    Explanations

    phrases related to telling or informing someone of something

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in communication or instruction

    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
    agra
    -0.69
    vantage
    -0.63
    xtap
    -0.59
    ords
    -0.59
    ypes
    -0.58
    \.
    -0.57
    inances
    -0.56
    cision
    -0.55
    aph
    -0.55
     contrad
    -0.53
    POSITIVE LOGITS
     goodbye
    0.99
     why
    0.85
     how
    0.85
     he
    0.83
     that
    0.82
     they
    0.79
     about
    0.79
     bluntly
    0.77
     what
    0.77
     she
    0.76
    Activations Density 0.110%

    No Known Activations