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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 13707
    Prev
    Next
    INDEX
    Explanations

    spokespersons mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespersons and their statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iHUD
    -0.66
    spir
    -0.64
     environmentalists
    -0.61
     dream
    -0.60
     "$:/
    -0.59
     convergence
    -0.59
     gou
    -0.57
     lumber
    -0.56
     killers
    -0.56
     dreaming
    -0.56
    POSITIVE LOGITS
     spokesman
    0.92
     spokesperson
    0.82
     spokeswoman
    0.79
    atoon
    0.79
     declined
    0.73
     emailed
    0.73
     confirmed
    0.71
    rored
    0.71
    geant
    0.71
     confirms
    0.69
    Activations Density 0.038%

    No Known Activations