© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14543
    Prev
    Next
    INDEX
    Explanations

    numerical values related to percentage or high scores

    oai_token-act-pair · gpt-3.5-turbo

    percentage values

    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
    rift
    -0.93
    mare
    -0.82
    worldly
    -0.73
    achi
    -0.72
    akers
    -0.70
    rang
    -0.70
    letal
    -0.70
    ake
    -0.68
    mares
    -0.68
    oles
    -0.68
    POSITIVE LOGITS
    00000
    1.10
    Percent
    0.93
    %"
    0.92
    %]
    0.88
    Hz
    0.84
    %;
    0.84
    644
    0.84
    +)
    0.82
    Mbps
    0.82
    0000
    0.81
    Activations Density 0.030%

    No Known Activations