© 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. 12-RES-JB
    11. 4680
    Prev
    Next
    INDEX
    Explanations

    last names of people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    CLASSIFIED
    -1.36
     millenn
    -1.30
    ô
    -1.27
     corrid
    -1.26
     behavi
    -1.24
     exha
    -1.23
    Þ
    -1.22
     newsp
    -1.21
    ß
    -1.16
     practition
    -1.14
    POSITIVE LOGITS
    l
    1.71
    lv
    1.41
    lon
    1.38
    len
    1.38
    rons
    1.35
    lio
    1.35
    ron
    1.34
    lc
    1.31
    late
    1.29
    lesi
    1.28
    Activations Density 0.347%

    No Known Activations