© 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. 2078
    Prev
    Next
    INDEX
    Explanations

    locations and states in the United States

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and their frequency in sentences

    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
    rix
    -0.70
    rupted
    -0.70
    ename
    -0.65
    aea
    -0.64
    itol
    -0.63
    miah
    -0.62
    \/
    -0.62
    frac
    -0.62
    chin
    -0.62
    "]=>
    -0.61
    POSITIVE LOGITS
     respectively
    2.32
     among
    1.30
    among
    1.25
     both
    1.16
     amongst
    1.11
     alike
    1.11
     etc
    1.10
    depending
    1.07
     whichever
    1.07
     plus
    1.04
    Activations Density 0.296%

    No Known Activations