© 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. 3221
    Prev
    Next
    INDEX
    Explanations

    phrases related to project collaboration, support, and growth

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

    variations of the word "end."

    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
    esome
    -0.71
    pillar
    -0.70
    pload
    -0.60
     Parables
    -0.58
    girl
    -0.57
    pex
    -0.56
    Pal
    -0.56
     assembled
    -0.55
    Forward
    -0.55
     Variant
    -0.55
    POSITIVE LOGITS
    angering
    1.36
    orses
    1.17
    angers
    1.13
     up
    1.10
    eared
    1.09
     abruptly
    1.04
    owment
    1.00
    ear
    1.00
     tragically
    0.99
    ures
    0.98
    Activations Density 0.059%

    No Known Activations