© 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. 4-RES-JB
    11. 16503
    Prev
    Next
    INDEX
    Explanations

    adjectives related to textures or physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that describe windy conditions or the experience of being in a windy environment

    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
    ajor
    -0.85
     Examiner
    -0.78
    atoon
    -0.67
    raltar
    -0.67
    aeda
    -0.67
    slave
    -0.67
    igslist
    -0.66
    ãĥ¯
    -0.66
    rongh
    -0.66
     vou
    -0.65
    POSITIVE LOGITS
    ielding
    0.88
    ield
    0.87
    ness
    0.85
    lly
    0.77
    uns
    0.77
     eyed
    0.75
    bye
    0.73
    oes
    0.73
    μ
    0.72
    kees
    0.71
    Activations Density 0.044%

    No Known Activations