© 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. 4226
    Prev
    Next
    INDEX
    Explanations

    specific facts or information

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

    possessive forms indicating ownership or attributes related to notable entities or subjects

    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
    ality
    -0.80
    xual
    -0.75
    =-=-
    -0.72
    Subject
    -0.71
    quished
    -0.70
    cffff
    -0.69
    adel
    -0.69
    ikawa
    -0.68
    aneers
    -0.67
    realDonaldTrump
    -0.66
    POSITIVE LOGITS
     foremost
    1.31
     tallest
    1.31
     largest
    1.29
     oldest
    1.27
     busiest
    1.20
     longest
    1.20
     richest
    1.19
     deadliest
    1.19
     smallest
    1.19
     biggest
    1.17
    Activations Density 0.091%

    No Known Activations