© 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. 9-RES-JB
    11. 14864
    Prev
    Next
    INDEX
    Explanations

    terms related to statistics or reports, specifically percentages and numbers

    oai_token-act-pair · gpt-3.5-turbo

    statistical information and percentages related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     versa
    -0.68
    Versions
    -0.66
    anwhile
    -0.65
     [*
    -0.63
    ogether
    -0.62
    vertisement
    -0.61
    ureau
    -0.61
     referen
    -0.60
    obbies
    -0.60
    entimes
    -0.60
    POSITIVE LOGITS
     Belfast
    0.76
     graphene
    0.74
     Xperia
    0.74
     SpaceX
    0.72
     Fukushima
    0.70
     bicycl
    0.69
     Hillary
    0.69
     âĢİ
    0.68
     cryptocurrency
    0.68
     Xiaomi
    0.67
    Activations Density 1.580%

    No Known Activations