© 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. 4-RES-JB
    11. 10534
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to infrastructure and engineering

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to structured systems and organizational elements

    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
    ¿½
    -0.83
    âĸ¬
    -0.75
    Reloaded
    -0.72
    èª
    -0.71
     conclud
    -0.71
    PDATE
    -0.69
    OHN
    -0.67
    SEA
    -0.67
    bidden
    -0.67
     corrid
    -0.66
    POSITIVE LOGITS
    hers
    0.76
    emo
    0.69
     ('
    0.69
    coon
    0.67
     ("
    0.65
    istry
    0.65
     Caps
    0.59
     capsules
    0.58
    naire
    0.57
     contam
    0.57
    Activations Density 0.966%

    No Known Activations