© 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. 8-RES-JB
    11. 11537
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or groups holding specific positions within organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating collaborative relationships and partnerships among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decency
    -0.78
     caveats
    -0.77
     uncertainties
    -0.76
     loopholes
    -0.76
     snap
    -0.73
     lapse
    -0.72
     kindness
    -0.72
     cubic
    -0.70
     realistically
    -0.68
     swoop
    -0.68
    POSITIVE LOGITS
    founder
    1.41
    director
    1.30
    leader
    1.24
    chair
    1.17
    founded
    1.13
    creator
    1.10
    authored
    1.08
    signed
    1.07
    found
    1.06
    Found
    1.05
    Activations Density 0.054%

    No Known Activations