© 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. 4009
    Prev
    Next
    INDEX
    Explanations

    nouns related to technology and software products

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

    sentences that convey personal experiences and actions related to technology and decision-making

    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
    ¿½
    -0.84
    aining
    -0.61
    INTON
    -0.58
    AGES
    -0.58
    Vict
    -0.58
    ittal
    -0.58
    Newsletter
    -0.58
    serving
    -0.58
    RANT
    -0.57
    YS
    -0.57
    POSITIVE LOGITS
     decided
    1.26
     resorted
    1.24
     devised
    1.08
     opted
    1.08
     embarked
    1.02
     enlisted
    0.99
     ventured
    0.94
     contacted
    0.93
     teamed
    0.91
     reluctantly
    0.89
    Activations Density 0.432%

    No Known Activations