© 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. 3-RES-JB
    11. 24087
    Prev
    Next
    INDEX
    Explanations

    terms related to universities, colleges, cities, and regions

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places, organizations, and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.62
     hindsight
    -0.56
    inarily
    -0.50
    iqueness
    -0.49
    pection
    -0.46
     deductible
    -0.45
    ulative
    -0.45
    omething
    -0.44
    untled
    -0.43
     varied
    -0.42
    POSITIVE LOGITS
     Ltd
    0.68
     âĵĺ
    0.64
     LTD
    0.58
    Joined
    0.57
     LLP
    0.53
     GDDR
    0.51
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.51
    ombat
    0.50
    akens
    0.48
    Ħ¢
    0.47
    Activations Density 2.152%

    No Known Activations