© 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. 11242
    Prev
    Next
    INDEX
    Explanations

    information related to communication or instructions

    oai_token-act-pair · gpt-3.5-turbo

    statements that summarize or provide conclusions

    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
     organise
    -0.78
     whilst
    -0.77
     Whilst
    -0.77
     organisers
    -0.75
     realise
    -0.75
     apologise
    -0.75
     util
    -0.73
     rumours
    -0.70
     fulfil
    -0.70
     exting
    -0.70
    POSITIVE LOGITS
     Slate
    0.62
     Whitman
    0.61
     Sullivan
    0.60
     POLITICO
    0.59
     skepticism
    0.56
     Rubin
    0.56
     staffers
    0.56
     analytic
    0.55
    Specifically
    0.54
     Greenberg
    0.54
    Activations Density 2.285%

    No Known Activations