© 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. 22125
    Prev
    Next
    INDEX
    Explanations

    phrases expressing contrasts or contradictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating qualification or limitation in various contexts

    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
    iHUD
    -0.72
    ãĤ§
    -0.67
    éĹĺ
    -0.61
    umbn
    -0.60
    pass
    -0.54
     è£ıè
    -0.54
    ãĥĭ
    -0.54
    RIP
    -0.54
    cair
    -0.54
    Released
    -0.53
    POSITIVE LOGITS
     does
    1.57
     do
    1.51
     did
    1.47
    does
    1.18
    did
    1.16
     are
    1.15
     Does
    1.13
     DOES
    1.07
     will
    1.03
    do
    1.03
    Activations Density 0.247%

    No Known Activations