© 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. 8-RES-JB
    11. 2616
    Prev
    Next
    INDEX
    Explanations

    technical instructions or commands related to software operations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    engineering
    -0.76
    JD
    -0.70
    quished
    -0.66
    Said
    -0.65
     vocational
    -0.65
    ressing
    -0.63
    foreseen
    -0.62
    Enough
    -0.61
    hea
    -0.60
    MU
    -0.60
    POSITIVE LOGITS
     be
    1.22
     gladly
    1.14
     suffice
    1.09
     overwrite
    1.09
     appear
    1.06
     automatically
    1.05
     vary
    1.00
     disappear
    0.99
     ALWAYS
    0.97
     expire
    0.97
    Activations Density 0.198%

    No Known Activations