© 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. 10-RES-JB
    11. 5325
    Prev
    Next
    INDEX
    Explanations

    string of characters resembling a technical code or ID

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic or organizational entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parameter
    -0.83
    ãĥķãĤ©
    -0.78
     Antar
    -0.77
    acid
    -0.77
    actionDate
    -0.76
     Mig
    -0.74
     acid
    -0.74
     Autism
    -0.73
     Assass
    -0.73
     Malone
    -0.72
    POSITIVE LOGITS
    W
    1.51
    w
    1.38
    WS
    1.36
    WA
    1.35
    WM
    1.32
     Wad
    1.30
    wb
    1.28
    wl
    1.25
    ws
    1.24
    WW
    1.24
    Activations Density 0.535%

    No Known Activations