© 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. 10-RES-JB
    11. 6059
    Prev
    Next
    INDEX
    Explanations

    phrases or words describing close similarity or alignment

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating close relationships or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inous
    -0.79
     abundantly
    -0.77
    acity
    -0.77
    amaz
    -0.70
    acious
    -0.68
    inally
    -0.68
    ane
    -0.67
     inval
    -0.65
    ICAN
    -0.64
    xit
    -0.63
    POSITIVE LOGITS
     resemble
    1.12
     resembles
    1.10
     resembled
    1.09
     resembling
    1.02
     guarded
    0.99
     aligned
    0.99
     monitored
    0.97
     allied
    0.94
     related
    0.93
     scrutin
    0.93
    Activations Density 0.045%

    No Known Activations