© 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. 9-RES-JB
    11. 10058
    Prev
    Next
    INDEX
    Explanations

    phrases containing the expression "believe it or not."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "believe it or not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.63
    liest
    -0.59
    enough
    -0.54
    cffffcc
    -0.54
     prematurely
    -0.52
    Enough
    -0.52
     =>
    -0.49
     (?,
    -0.49
    ummer
    -0.48
    still
    -0.48
    POSITIVE LOGITS
    hig
    0.54
    emia
    0.50
    adow
    0.49
    og
    0.48
    Bench
    0.48
    «
    0.48
    izens
    0.48
    ry
    0.46
    ogs
    0.46
    inos
    0.46
    Activations Density 1.003%

    No Known Activations