© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7333
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ness' and 'ism'

    oai_token-act-pair · gpt-3.5-turbo

    suffixed forms of words that indicate states, conditions, or ideologies

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

    No Comments

    Negative Logits
     embell
    -0.66
    backs
    -0.64
    illac
    -0.59
    iety
    -0.59
    yright
    -0.59
    button
    -0.58
     embro
    -0.56
     raping
    -0.56
    advertising
    -0.56
    acting
    -0.56
    POSITIVE LOGITS
    mun
    0.83
     ILCS
    0.78
     Kits
    0.74
    erver
    0.73
    sembly
    0.72
    ea
    0.71
     Immun
    0.69
     Matters
    0.68
    e
    0.68
     Corps
    0.67
    Activations Density 0.052%

    No Known Activations