© 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. 11-RES-JB
    11. 18598
    Prev
    Next
    INDEX
    Explanations

    phrases related to triggers or activations

    oai_token-act-pair · gpt-3.5-turbo

    words related to traditional or formal categories

    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
     condem
    -0.59
     livelihood
    -0.58
     medium
    -0.58
     innocence
    -0.57
     fetch
    -0.56
     appraisal
    -0.55
     welcome
    -0.55
     Reincarn
    -0.54
     Prohibition
    -0.54
     ransom
    -0.53
    POSITIVE LOGITS
    itionally
    1.04
    lycer
    0.96
    portation
    0.86
    bish
    0.85
    MpServer
    0.77
    ulously
    0.74
    imensional
    0.73
    ulence
    0.73
    ecast
    0.73
    ajo
    0.73
    Activations Density 0.069%

    No Known Activations