© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 4771
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software, games, or specific events and awards

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of media and notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¦
    -0.64
    ãĥ¼ãĥĨ
    -0.62
    Tags
    -0.60
    inders
    -0.59
    Americans
    -0.59
     NPCs
    -0.58
    ensibly
    -0.58
    inflamm
    -0.57
    oser
    -0.57
    zbollah
    -0.57
    POSITIVE LOGITS
     vicinity
    1.17
     category
    1.16
     vein
    1.16
     context
    1.10
     realm
    1.08
     manner
    1.02
     arena
    0.99
     guise
    0.99
     era
    0.98
     area
    0.96
    Activations Density 0.561%

    No Known Activations