© 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. 12-RES-JB
    11. 4004
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a critical or certain statement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    negations and phrases indicating absence or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    lished
    -0.70
    20439
    -0.70
    ËĪ
    -0.65
    ilian
    -0.62
    thouse
    -0.61
    come
    -0.60
    cano
    -0.60
    ngth
    -0.59
    adic
    -0.58
    iday
    -0.58
    POSITIVE LOGITS
     mistake
    0.69
     ponies
    0.60
     misunderstanding
    0.57
    iners
    0.56
    itus
    0.55
     deficiency
    0.55
    lements
    0.54
     Conversation
    0.54
    ine
    0.54
     Plans
    0.52
    Activations Density 0.174%

    No Known Activations