© 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. 3-RES-JB
    11. 22892
    Prev
    Next
    INDEX
    Explanations

    phrases related to performing actions

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the"

    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
    SPONSORED
    -0.65
    /
    -0.64
    âĢij
    -0.62
    Param
    -0.60
    HAEL
    -0.59
    ccoli
    -0.59
    ().
    -0.58
    craft
    -0.57
    onse
    -0.57
    arry
    -0.57
    POSITIVE LOGITS
     same
    1.24
     entire
    1.22
     latter
    1.13
     fastest
    1.12
     quickest
    1.09
     hardest
    1.08
    ses
    1.06
     slightest
    1.05
     latest
    1.05
     remainder
    1.03
    Activations Density 1.263%

    No Known Activations