© 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. 1-RES-JB
    11. 14362
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names ending with 'ho'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the expression "ho" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commonwealth
    -0.78
    ãĥ¡
    -0.75
    Interstitial
    -0.72
     totality
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
     Terms
    -0.68
    ividual
    -0.66
     Newsp
    -0.66
     Consent
    -0.66
     ICC
    -0.65
    POSITIVE LOGITS
    ho
    1.09
    hoe
    1.07
    ppy
    1.06
    ppo
    1.03
    pping
    1.02
    oney
    1.02
    jo
    0.99
    efully
    0.97
    ffer
    0.97
    arding
    0.96
    Activations Density 0.003%

    No Known Activations