© 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. 6-RES-JB
    11. 2997
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially those with the letter "H" as a prominent feature in their name

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.84
    prone
    -0.65
    netflix
    -0.63
    Balt
    -0.60
    usercontent
    -0.59
    Dex
    -0.59
    omnia
    -0.59
    SOURCE
    -0.58
    abytes
    -0.57
    minecraft
    -0.57
    POSITIVE LOGITS
    amins
    0.77
    ħĭ
    0.76
    igi
    0.68
     reconc
    0.64
    ixie
    0.63
    hof
    0.63
    wagen
    0.62
    ĵĺ
    0.62
    ovic
    0.60
     Ribbon
    0.59
    Activations Density 0.103%

    No Known Activations