© 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. 3358
    Prev
    Next
    INDEX
    Explanations

    people's names or nicknames

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and identifiers within a context

    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
     Brist
    -0.86
     Cassandra
    -0.82
     Payton
    -0.82
     Shel
    -0.81
     Carb
    -0.79
     Melissa
    -0.77
     Carn
    -0.76
     Matthews
    -0.74
     Lynd
    -0.74
     Brooke
    -0.73
    POSITIVE LOGITS
    u
    1.73
    Å«
    1.60
    ut
    1.52
    uj
    1.50
    uz
    1.48
    ui
    1.48
    uk
    1.46
    uc
    1.44
    uh
    1.43
    uf
    1.42
    Activations Density 0.293%

    No Known Activations