© 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. 9-RES-JB
    11. 20736
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or decisions being taken

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "do" in various contexts

    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
    mares
    -0.65
     Frie
    -0.57
     ascended
    -0.56
    Rank
    -0.56
    lights
    -0.55
    ulative
    -0.54
    Hung
    -0.53
    uses
    -0.53
    hung
    -0.51
    hog
    -0.51
    POSITIVE LOGITS
    oms
    1.00
    ppel
    1.00
    omsday
    0.96
    oming
    0.91
    lez
    0.86
    vet
    0.84
    xx
    0.82
     likewise
    0.81
     nothing
    0.81
     justice
    0.80
    Activations Density 0.140%

    No Known Activations