© 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. 11988
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political terms

    oai_token-act-pair · gpt-3.5-turbo

    the acronym "PAT" and related terms associated with it

    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
    Rom
    -0.84
     Dong
    -0.80
     Strauss
    -0.79
     Gladiator
    -0.79
     Rapp
    -0.78
    egal
    -0.76
     Machina
    -0.76
     Holden
    -0.75
     Bloom
    -0.75
    Ocean
    -0.73
    POSITIVE LOGITS
     PAT
    2.91
     PK
    1.68
     sock
    1.36
     PKK
    1.35
     socks
    1.23
     NET
    1.17
     Pats
    1.15
     YPG
    1.15
    PK
    1.14
     COL
    1.13
    Activations Density 0.054%

    No Known Activations