© 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 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. 2324
    Prev
    Next
    INDEX
    Explanations

    plural verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements involving the word "do."

    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
     countered
    -0.61
    hog
    -0.59
    opol
    -0.58
     Ages
    -0.57
    ħĭ
    -0.56
    anon
    -0.56
     Printed
    -0.55
     inflated
    -0.55
    ONSORED
    -0.54
     Islands
    -0.54
    POSITIVE LOGITS
    pez
    1.01
    zed
    1.00
    omsday
    0.95
    oms
    0.93
    actic
    0.89
     manage
    0.84
    zing
    0.79
     not
    0.78
    ppel
    0.77
    gging
    0.77
    Activations Density 0.107%

    No Known Activations