© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6550
    Prev
    Next
    INDEX
    Explanations

    scientific concepts or medical terms related to procedures and documentation

    oai_token-act-pair · gpt-3.5-turbo

    recurring mentions of "the" and related phrases that establish connections or references to a subject

    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
    Europe
    -0.68
    ornings
    -0.68
    enko
    -0.67
    perse
    -0.67
    doms
    -0.66
    skirts
    -0.65
    tips
    -0.64
    Brexit
    -0.64
    amar
    -0.64
     Zup
    -0.63
    POSITIVE LOGITS
     person
    1.50
     recipient
    1.45
     wearer
    1.35
     perpetrator
    1.35
     offending
    1.33
     offender
    1.26
     attacker
    1.24
     applicant
    1.24
     underlying
    1.24
     claimant
    1.21
    Activations Density 0.489%

    No Known Activations