© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11112
    Prev
    Next
    INDEX
    Explanations

    individuals involved in specific events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships and connections between people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĦ¢:
    -0.75
     gladly
    -0.68
    Includes
    -0.63
    ###
    -0.62
    places
    -0.62
     anytime
    -0.62
     sts
    -0.61
    ®
    -0.60
    verages
    -0.58
    abouts
    -0.58
    POSITIVE LOGITS
     another
    1.10
     hers
    1.02
     an
    0.98
     one
    0.95
     a
    0.93
     someone
    0.90
     theirs
    0.85
    another
    0.84
     his
    0.80
     somebody
    0.73
    Activations Density 0.648%

    No Known Activations