© 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. 9-RES-JB
    11. 16607
    Prev
    Next
    INDEX
    Explanations

    comparisons where something is considered superior or preferable to something else

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating something is better than another

    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
    LIN
    -0.80
    ango
    -0.80
     Topics
    -0.79
    olson
    -0.72
    neys
    -0.70
    */(
    -0.69
    uria
    -0.69
    ULE
    -0.69
    avi
    -0.69
    bard
    -0.68
    POSITIVE LOGITS
     useless
    1.00
     anything
    0.93
     crap
    0.86
     theirs
    0.86
     anybody
    0.86
     worthless
    0.83
     mediocre
    0.82
     guessing
    0.81
     nothing
    0.80
     ours
    0.79
    Activations Density 0.097%

    No Known Activations