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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12622
    Prev
    Next
    INDEX
    Explanations

    objects or elements in a physical space

    oai_token-act-pair · gpt-3.5-turbo

    objects and beings associated with chaotic or crowded environments

    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
    ISA
    -0.80
    elist
    -0.69
     Partnership
    -0.64
     successor
    -0.63
    Solution
    -0.62
    YL
    -0.62
    idates
    -0.61
     Corrections
    -0.61
    guyen
    -0.60
     nominees
    -0.60
    POSITIVE LOGITS
     buzzing
    1.26
     crawling
    1.21
     everywhere
    1.17
     raining
    1.17
     blazing
    1.16
     popping
    1.15
     circling
    1.14
    creen
    1.13
    hips
    1.12
     roaring
    1.10
    Activations Density 0.304%

    No Known Activations