© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13127
    Prev
    Next
    INDEX
    Explanations

    mentions of separatists and technological specifications related to graphics cards

    oai_token-act-pair · gpt-3.5-turbo

    mentions of separatist groups and geographical references related to their activities

    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
    SON
    -0.71
     SERV
    -0.70
     Ze
    -0.68
     Ike
    -0.67
    Lev
    -0.66
     Meyer
    -0.66
     Ali
    -0.65
     Stud
    -0.65
     Fav
    -0.64
     Manuel
    -0.64
    POSITIVE LOGITS
     separatists
    3.07
     separatist
    2.64
     secession
    1.71
     separat
    1.69
     Donetsk
    1.51
    ansk
    1.47
     GTX
    1.44
     sovere
    1.11
     Catalonia
    1.08
    Catal
    1.03
    Activations Density 0.025%

    No Known Activations