© 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. 4435
    Prev
    Next
    INDEX
    Explanations

    requests for feedback or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases requesting feedback or information

    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
    ItemTracker
    -0.88
    ĪĴ
    -0.86
    tein
    -0.62
     Chatt
    -0.62
     Wand
    -0.61
    phrine
    -0.59
    obs
    -0.59
    orie
    -0.59
     sqor
    -0.59
     Mug
    -0.58
    POSITIVE LOGITS
    ledged
    0.86
    raq
    0.83
    ariat
    0.80
     beforehand
    0.73
    URE
    0.71
    lege
    0.71
    ÑĮ
    0.69
    ubes
    0.68
    oway
    0.68
    reprene
    0.68
    Activations Density 0.025%

    No Known Activations