© 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. 3-RES-JB
    11. 12684
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    actions related to measurement, manipulation, and physical interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.53
    foundland
    -0.45
     subur
    -0.44
     promoter
    -0.44
     CLSID
    -0.41
    é¾įå
    -0.39
    dating
    -0.38
     afore
    -0.38
     Moroc
    -0.38
    thus
    -0.37
    POSITIVE LOGITS
    ings
    0.51
     ANY
    0.49
    ments
    0.48
     them
    0.47
    INGS
    0.47
    uate
    0.47
     yourselves
    0.46
     him
    0.46
    olate
    0.45
    nces
    0.44
    Activations Density 1.264%

    No Known Activations