© 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. 9-RES-JB
    11. 11173
    Prev
    Next
    INDEX
    Explanations

    aspects related to the technical quality and production values of a creative work

    oai_token-act-pair · gpt-3.5-turbo

    elements related to filmmaking and video game design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iatus
    -0.81
    inel
    -0.78
    icer
    -0.74
    isance
    -0.74
    ŃĶ
    -0.73
    ģĸ
    -0.73
    cot
    -0.72
    ishable
    -0.71
    Joined
    -0.71
    20439
    -0.70
    POSITIVE LOGITS
     quirks
    1.15
     resemblance
    1.12
     resemb
    1.03
     similarities
    1.00
     resembles
    0.97
     varies
    0.96
     similarity
    0.91
     aspect
    0.87
     choices
    0.84
     differs
    0.84
    Activations Density 0.366%

    No Known Activations