© 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. 21075
    Prev
    Next
    INDEX
    Explanations

    the name 'Steve' in texts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Steve."

    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
    teen
    -0.74
    ktop
    -0.73
     hereby
    -0.62
    pec
    -0.61
     pace
    -0.60
    tera
    -0.60
     ceilings
    -0.60
    icular
    -0.59
    words
    -0.58
    een
    -0.58
    POSITIVE LOGITS
     Jobs
    1.18
     Bannon
    1.03
     Irwin
    0.98
     Sail
    0.96
     Wyn
    0.86
     Madden
    0.86
     Ange
    0.83
     Kro
    0.83
     Kerr
    0.82
     Reich
    0.82
    Activations Density 0.022%

    No Known Activations