© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8668
    Prev
    Next
    INDEX
    Explanations

    food and beverage-related words

    oai_token-act-pair · gpt-3.5-turbo

    action verbs and dynamic situations

    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
    Were
    -0.64
    were
    -0.64
    biased
    -0.61
     ensued
    -0.59
    ombo
    -0.58
     constituted
    -0.58
    anooga
    -0.58
     differed
    -0.57
     ourselves
    -0.57
    aum
    -0.56
    POSITIVE LOGITS
     himself
    0.92
     his
    0.91
     herself
    0.84
     HIS
    0.70
     His
    0.69
    His
    0.68
    his
    0.65
     he
    0.64
     sings
    0.64
     keeps
    0.64
    Activations Density 1.958%

    No Known Activations