© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 14215
    Prev
    Next
    INDEX
    Explanations

    mentions of communism or related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to communication and its various forms related to communities, specifically in the context of social and political structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pity
    -0.65
    TEXTURE
    -0.64
    toe
    -0.64
     Brill
    -0.63
    steen
    -0.61
    HER
    -0.60
     Leigh
    -0.60
    BALL
    -0.59
     Lot
    -0.58
    Winner
    -0.58
    POSITIVE LOGITS
    icator
    1.23
    icate
    1.19
    ications
    1.16
    ication
    1.15
    icating
    1.15
    icators
    1.14
    namese
    1.14
    icated
    1.12
    icable
    1.09
    icates
    1.07
    Activations Density 0.009%

    No Known Activations