© 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. 11328
    Prev
    Next
    INDEX
    Explanations

    numbers indicating steps or rules to follow

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and permissions

    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
    quickShipAvailable
    -0.81
    soType
    -0.76
    afety
    -0.70
     repercussions
    -0.69
     scares
    -0.69
    proven
    -0.67
    GoldMagikarp
    -0.67
     ramifications
    -0.65
     Lessons
    -0.64
    ONSORED
    -0.64
    POSITIVE LOGITS
     choose
    1.34
     utilize
    1.28
     receive
    1.27
     obtain
    1.22
     accumulate
    1.21
     use
    1.19
     omit
    1.18
     allocate
    1.18
     participate
    1.16
     spend
    1.16
    Activations Density 0.319%

    No Known Activations