© 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. 11-RES-JB
    11. 95
    Prev
    Next
    INDEX
    Explanations

    texts discussing the nature of a situation or an issue

    oai_token-act-pair · gpt-3.5-turbo

    statements related to reality and political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.65
    peed
    -0.62
     Dunk
    -0.59
     forgiven
    -0.59
     dstg
    -0.58
     Mile
    -0.57
    ãĥĺ
    -0.57
    Reviewer
    -0.55
     defe
    -0.54
    Letter
    -0.54
    POSITIVE LOGITS
    's
    1.08
    ÃŃs
    1.06
     involves
    1.00
     reflects
    0.94
     belongs
    0.93
     represents
    0.92
     is
    0.89
     relates
    0.88
    'm
    0.88
    're
    0.85
    Activations Density 0.139%

    No Known Activations