© 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. 11-RES-JB
    6. 1273
    Prev
    Next
    INDEX
    Explanations

    characters' names preceded by a comma

    oai_token-act-pair · gpt-3.5-turbo

    elements of dialogue or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nid
    -0.79
    zbollah
    -0.78
    ãĥ¥
    -0.75
     lithium
    -0.73
     chloride
    -0.72
    ikarp
    -0.71
     Kund
    -0.70
    brance
    -0.70
    153
    -0.70
     recharge
    -0.70
    POSITIVE LOGITS
    George
    2.28
     George
    2.19
     Georg
    1.46
    Georg
    1.33
    ORGE
    1.18
     GW
    1.09
     GE
    1.05
     Trayvon
    1.04
     Ralph
    0.97
     Soros
    0.95
    Activations Density 0.184%

    No Known Activations