© 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. 0-RES-JB
    11. 8254
    Prev
    Next
    INDEX
    Explanations

    broadcast TV show schedules

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ANN" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thief
    -0.86
     Escape
    -0.71
    knife
    -0.69
     Zub
    -0.66
    cible
    -0.65
    ificantly
    -0.65
    itive
    -0.64
     Magicka
    -0.64
     Zone
    -0.63
    lime
    -0.63
    POSITIVE LOGITS
    ANN
    4.41
     ANN
    2.40
    ann
    2.34
    ANA
    1.98
    Ann
    1.84
    anni
    1.54
     Ann
    1.32
    annie
    1.29
    iann
    1.27
     ann
    1.24
    Activations Density 0.020%

    No Known Activations