© 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. 7398
    Prev
    Next
    INDEX
    Explanations

    names of professional associations and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to professional associations and groups

    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
    lier
    -0.77
    efully
    -0.70
    rous
    -0.63
     fisherman
    -0.63
    liest
    -0.62
     fisher
    -0.62
     manipulation
    -0.61
     launcher
    -0.61
    OSS
    -0.61
     conversion
    -0.60
    POSITIVE LOGITS
    hip
    1.26
    paces
    1.19
    pace
    1.07
    mith
    1.05
    '
    1.03
     Associ
    1.03
     Association
    1.02
    haw
    1.01
    hips
    1.01
     Guild
    1.01
    Activations Density 0.168%

    No Known Activations