© 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. 10-RES-JB
    11. 13910
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures or events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DOE
    -0.88
    ISON
    -0.83
    Bernie
    -0.82
    heit
    -0.81
    Recommend
    -0.80
     Autism
    -0.75
     Cosponsors
    -0.75
    raviolet
    -0.74
    LAB
    -0.74
    daq
    -0.74
    POSITIVE LOGITS
     Ottoman
    1.49
     medieval
    1.43
     Romans
    1.41
     Medieval
    1.39
     Byzantine
    1.38
     kings
    1.37
     Byz
    1.34
     ancient
    1.34
     empires
    1.32
     pagan
    1.31
    Activations Density 0.712%

    No Known Activations