© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15684
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical and scientific modeling

    oai_token-act-pair · gpt-3.5-turbo

    statements related to scientific modeling and analysis

    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
    eur
    -0.79
     Toast
    -0.74
     rite
    -0.72
     Kills
    -0.70
    NetMessage
    -0.70
     Piercing
    -0.69
     Signs
    -0.67
     deeds
    -0.67
     Steal
    -0.66
     cringe
    -0.66
    POSITIVE LOGITS
     simulations
    1.53
     modelling
    1.47
     modeling
    1.41
     models
    1.34
     simulate
    1.31
     simulated
    1.31
    models
    1.28
     predictions
    1.27
     model
    1.27
     predicting
    1.27
    Activations Density 0.315%

    No Known Activations