© 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. 3-RES-JB
    11. 21073
    Prev
    Next
    INDEX
    Explanations

    profane and offensive language

    oai_token-act-pair · gpt-3.5-turbo

    profanity and vulgar expressions

    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
    Specific
    -0.80
    Recomm
    -0.79
    WP
    -0.78
    universal
    -0.72
    channelAvailability
    -0.72
    Develop
    -0.71
    wcs
    -0.69
     opposed
    -0.68
    çĦ
    -0.68
    Chel
    -0.66
    POSITIVE LOGITS
    ruary
    0.99
    acci
    0.76
    peat
    0.75
    glers
    0.70
    ér
    0.70
    uffs
    0.70
     stink
    0.68
    illet
    0.67
    ishly
    0.67
    ancial
    0.66
    Activations Density 0.064%

    No Known Activations