© 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. 4415
    Prev
    Next
    INDEX
    Explanations

    the word "unbeknownst" or variations of the word in different contexts

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

    the presence of the prefix "unb" indicating negation or absence

    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
     antioxid
    -0.79
     Yen
    -0.71
     Okinawa
    -0.70
     Vera
    -0.67
     Hots
    -0.67
     Confederation
    -0.66
     Azerbaijan
    -0.66
     Bengal
    -0.66
     Cot
    -0.66
     Klingon
    -0.64
    POSITIVE LOGITS
    earance
    1.46
    idding
    1.42
    iblical
    1.39
    urden
    1.37
    anked
    1.36
    urd
    1.34
    ounded
    1.32
    idden
    1.28
    udget
    1.28
    odied
    1.25
    Activations Density 0.050%

    No Known Activations