© 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. 9-RES-JB
    11. 23016
    Prev
    Next
    INDEX
    Explanations

    quantifiers and comparisons related to size

    oai_token-act-pair · gpt-3.5-turbo

    references to size or magnitude

    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
    mates
    -0.77
    inances
    -0.68
    aired
    -0.68
    speak
    -0.67
    straight
    -0.65
     mates
    -0.64
    mate
    -0.64
     Methods
    -0.64
    aline
    -0.63
    ilda
    -0.63
    POSITIVE LOGITS
     discrepancy
    1.18
     disparity
    1.17
     deficits
    1.13
     gap
    1.10
     difference
    1.07
     disparities
    1.06
     swath
    1.05
     discrepancies
    1.04
     impact
    1.04
     influx
    1.03
    Activations Density 0.321%

    No Known Activations