© 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. 11-RES-JB
    6. 948
    Prev
    Next
    INDEX
    Explanations

    surroundings or things that are being observed and commented on astutely

    oai_token-act-pair · gpt-3.5-turbo

    references to astrology or astrological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     fluids
    -0.63
     Orig
    -0.62
     trickle
    -0.60
     admission
    -0.59
     sentences
    -0.59
    æĢ
    -0.58
    ãĥ¯
    -0.57
     Bett
    -0.57
     Borderlands
    -0.57
     headers
    -0.56
    POSITIVE LOGITS
    rolog
    1.44
    igmat
    1.42
    rology
    1.41
    roph
    1.33
    ounding
    1.28
    ral
    1.27
    rol
    1.23
    rament
    1.21
    rog
    1.18
    rom
    1.15
    Activations Density 0.031%

    No Known Activations