© 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. 0-RES-JB
    6. 11790
    Prev
    Next
    INDEX
    Explanations

    acronyms "CAFE" with numbers associated with each occurrence

    oai_token-act-pair · gpt-3.5-turbo

    references to the Canadian Association for Equality (CAFE) and related discussions

    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
     bucket
    -0.75
     trash
    -0.75
     Nets
    -0.74
     bag
    -0.71
     nets
    -0.68
     ré
    -0.67
     tant
    -0.66
     ledger
    -0.65
     salad
    -0.65
     Miliband
    -0.64
    POSITIVE LOGITS
    FE
    4.23
     FE
    2.48
    fe
    1.63
    ZE
    1.46
    Fe
    1.42
    FF
    1.42
    FA
    1.37
    FO
    1.31
    FD
    1.29
    FU
    1.25
    Activations Density 0.010%

    No Known Activations