© 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. 6430
    Prev
    Next
    INDEX
    Explanations

    time-related events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to lengthy formal proceedings or testimonies

    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
    ovan
    -0.86
    finder
    -0.76
    abiding
    -0.70
    MpServer
    -0.68
    etheless
    -0.67
    uggle
    -0.66
     cooper
    -0.65
     Finder
    -0.65
    vantage
    -0.62
    utenant
    -0.62
    POSITIVE LOGITS
     speech
    1.76
     keynote
    1.61
     speeches
    1.61
     remarks
    1.58
     Speech
    1.44
     lecture
    1.40
     address
    1.37
    speech
    1.35
     sermon
    1.30
     Address
    1.27
    Activations Density 0.309%

    No Known Activations