© 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. 22114
    Prev
    Next
    INDEX
    Explanations

    titles, announcements, and reports

    oai_token-act-pair · gpt-3.5-turbo

    items related to media releases and announcements

    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
    é¾įå
    -0.70
    ãģĻ
    -0.61
    ãģĦ
    -0.57
    $.
    -0.57
     advers
    -0.56
     undet
    -0.56
    ãĤĭ
    -0.56
     transact
    -0.53
    arcer
    -0.53
    POSE
    -0.53
    POSITIVE LOGITS
     âĵĺ
    0.78
     consists
    0.64
     Trip
    0.60
     contains
    0.60
    odcast
    0.56
    lessly
    0.56
    stores
    0.55
     reacts
    0.55
     looms
    0.54
    maker
    0.54
    Activations Density 0.847%

    No Known Activations