© 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. 0-RES-JB
    11. 11817
    Prev
    Next
    INDEX
    Explanations

    phrases related to scandals and actors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scandals and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     optimum
    -0.68
     equivalents
    -0.66
     cushion
    -0.61
     Fiscal
    -0.61
     smoked
    -0.60
    TERN
    -0.60
     satisfaction
    -0.60
    ³³³³³³³³³³³³³³³³
    -0.60
     Tactical
    -0.60
    heit
    -0.59
    POSITIVE LOGITS
    andal
    3.13
    actor
    2.78
    andals
    1.94
    anova
    1.05
    factor
    0.86
    Lex
    0.86
    idel
    0.85
    agin
    0.84
    aper
    0.83
    andel
    0.83
    Activations Density 0.010%

    No Known Activations