© 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. 24451
    Prev
    Next
    INDEX
    Explanations

    phrases indicating anticipation or prediction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote predictions or forecasts about future events

    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
    rehens
    -0.71
    natureconservancy
    -0.60
    izoph
    -0.58
    orno
    -0.57
    earch
    -0.56
     Wrong
    -0.55
    conservancy
    -0.54
    brush
    -0.53
     Conce
    -0.52
     IMAGES
    -0.50
    POSITIVE LOGITS
     to
    1.04
    æ©
    0.69
    plete
    0.66
    to
    0.66
     sometime
    0.65
     soon
    0.64
    ered
    0.63
    ly
    0.63
     someday
    0.63
    ĭ
    0.61
    Activations Density 0.056%

    No Known Activations