© 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. 3552
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or figures, specifically focusing on descriptions of people, races, and nationalities

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

    phrases indicating comparison or superlative qualities

    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
    PsyNetMessage
    -0.80
    inoa
    -0.77
    osponsors
    -0.76
    isks
    -0.76
    EStream
    -0.74
    */(
    -0.74
    IDS
    -0.73
    escription
    -0.73
    osterone
    -0.73
    okers
    -0.73
    POSITIVE LOGITS
     exalted
    1.24
     sublime
    1.24
     noble
    1.22
     glorious
    1.21
     magnificent
    1.21
     marvelous
    1.21
     precious
    1.20
     splendid
    1.17
     beautiful
    1.16
     wonderful
    1.15
    Activations Density 0.209%

    No Known Activations