© 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. 12080
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in various fields like journalism, business, and politics

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    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
    Ħ¢
    -0.59
     scen
    -0.51
    taboola
    -0.51
     spell
    -0.51
    omething
    -0.50
    late
    -0.50
    NUM
    -0.50
     rival
    -0.49
     commercially
    -0.49
     conditional
    -0.49
    POSITIVE LOGITS
     Nichols
    0.85
     agrees
    0.83
     welcomes
    0.81
     writes
    0.81
     discusses
    0.79
     acknowledges
    0.79
     Rosenberg
    0.78
     recommends
    0.78
     believes
    0.78
     Klein
    0.78
    Activations Density 0.305%

    No Known Activations