© 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. 8-RES-JB
    11. 7855
    Prev
    Next
    INDEX
    Explanations

    words related to different types of institutions or establishments

    oai_token-act-pair · gpt-3.5-turbo

    various forms of media and public spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PDATE
    -0.71
    ãĥį
    -0.69
    DEN
    -0.63
    noon
    -0.60
     downside
    -0.60
     totality
    -0.59
     Tycoon
    -0.58
     circumstance
    -0.57
    76561
    -0.56
     tremend
    -0.56
    POSITIVE LOGITS
     etc
    1.30
    mith
    1.18
    hips
    1.14
    paces
    1.07
    etc
    0.96
    cript
    0.94
    poons
    0.89
    hip
    0.88
    folk
    0.87
    hops
    0.85
    Activations Density 0.192%

    No Known Activations