© 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. 9-RES-JB
    11. 16582
    Prev
    Next
    INDEX
    Explanations

    specific characters used in text formatting

    oai_token-act-pair · gpt-3.5-turbo

    references to technical issues or problems in public services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.84
    andowski
    -0.81
     favors
    -0.79
     INS
    -0.78
     Takeru
    -0.77
    amsung
    -0.75
    defense
    -0.72
     cum
    -0.72
    illus
    -0.72
     Asuka
    -0.72
    POSITIVE LOGITS
     CBC
    1.42
     Aboriginal
    1.34
    CBC
    1.30
     NDP
    1.26
     Manitoba
    1.22
     Trudeau
    1.21
     Centre
    1.20
     councillors
    1.19
     councillor
    1.18
     Indigenous
    1.17
    Activations Density 0.543%

    No Known Activations