© 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. 10159
    Prev
    Next
    INDEX
    Explanations

    common surnames or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    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
     BI
    -0.70
     infographic
    -0.70
     Graphic
    -0.70
     Sovereign
    -0.69
     enthusi
    -0.68
     FORM
    -0.66
     wholesale
    -0.66
     pione
    -0.65
     Uni
    -0.65
     RIS
    -0.64
    POSITIVE LOGITS
    obar
    0.91
    rette
    0.84
    anyahu
    0.82
    vals
    0.81
    ady
    0.81
    rano
    0.81
    orius
    0.80
    usky
    0.79
    foo
    0.79
    ison
    0.78
    Activations Density 0.164%

    No Known Activations