© 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. 18533
    Prev
    Next
    INDEX
    Explanations

    terms related to stances or positions on various issues

    oai_token-act-pair · gpt-3.5-turbo

    references to someone's stance or position on various issues

    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
    batch
    -0.75
    chemy
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.66
    ombies
    -0.63
     unsuspecting
    -0.62
    loo
    -0.62
    gallery
    -0.62
     destro
    -0.60
     stuffing
    -0.60
    trap
    -0.59
    POSITIVE LOGITS
     stances
    1.20
     stance
    1.17
     toward
    1.08
     regarding
    1.06
     towards
    1.03
     favoring
    0.97
     on
    0.92
     concerning
    0.89
     vis
    0.89
     upholding
    0.88
    Activations Density 0.180%

    No Known Activations