© 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. 18578
    Prev
    Next
    INDEX
    Explanations

    names or titles of people, organizations, or entities in a digital context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific media or promotional content

    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
     weakened
    -0.88
     shielding
    -0.79
     combination
    -0.79
     prolong
    -0.79
     ransom
    -0.78
     speeding
    -0.77
     strengthening
    -0.77
     sustained
    -0.77
     slowing
    -0.77
     lining
    -0.77
    POSITIVE LOGITS
    Gaming
    1.31
    Planet
    1.25
    Gamer
    1.23
    Apps
    1.21
    Magazine
    1.16
    Nation
    1.15
    Truth
    1.15
    Sports
    1.13
    Blog
    1.13
    pedia
    1.12
    Activations Density 0.456%

    No Known Activations