© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10304
    Prev
    Next
    INDEX
    Explanations

    mentions of violent events or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights violations and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NX
    -0.62
    10000
    -0.61
     Proper
    -0.61
     ENT
    -0.61
    ////////////////
    -0.59
     Omn
    -0.58
    omorph
    -0.58
    200000
    -0.58
     Folder
    -0.57
     stere
    -0.56
    POSITIVE LOGITS
     crackdown
    0.93
     blamed
    0.90
     intensified
    0.86
     militants
    0.84
     accuse
    0.83
     strained
    0.82
     fears
    0.82
     sparking
    0.81
     deepening
    0.81
     worsening
    0.81
    Activations Density 1.041%

    No Known Activations