© 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. 18544
    Prev
    Next
    INDEX
    Explanations

    references to unverified or disputed events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to allegations of misconduct or wrongdoing

    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
    uden
    -0.84
    cair
    -0.82
    utics
    -0.82
    gaard
    -0.80
    oton
    -0.80
    vier
    -0.79
    uits
    -0.77
    wyn
    -0.76
    ovember
    -0.75
    ciating
    -0.75
    POSITIVE LOGITS
     wrongdoing
    1.09
     culprit
    1.06
     perpetrator
    1.03
     violations
    0.98
     mishand
    0.96
     misconduct
    0.95
     complicity
    0.94
     threats
    0.93
     misuse
    0.93
     threat
    0.93
    Activations Density 0.082%

    No Known Activations