© 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. 9-RES-JB
    11. 11142
    Prev
    Next
    INDEX
    Explanations

    specific days mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days, particularly the terms "day 7" and "day 8."

    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
    ngth
    -0.82
    ategory
    -0.79
    bourg
    -0.73
     externalToEVAOnly
    -0.69
    ancies
    -0.69
    thora
    -0.69
    emale
    -0.68
    negie
    -0.68
    obal
    -0.68
     Osw
    -0.67
    POSITIVE LOGITS
    dream
    1.54
    care
    1.20
    lights
    0.91
    break
    0.90
    motion
    0.86
    light
    0.86
    nings
    0.80
    BOOK
    0.80
    long
    0.79
    call
    0.78
    Activations Density 0.070%

    No Known Activations