© 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. 10-RES-JB
    11. 3256
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing certainty or promise/assertiveness

    oai_token-act-pair · gpt-3.5-turbo

    the presence of repeated symbols or characters, specifically the character "Ļ"

    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
    omore
    -0.59
     contempor
    -0.58
     Lithuan
    -0.57
    nington
    -0.57
     Lap
    -0.56
     decom
    -0.55
     Laurent
    -0.55
     Lumia
    -0.55
     lame
    -0.54
    auga
    -0.54
    POSITIVE LOGITS
    s
    0.95
    º
    0.89
    ¹
    0.81
    t
    0.79
    âĶĢ
    0.79
    °
    0.78
    ept
    0.77
    u
    0.74
    ulty
    0.73
    ²
    0.72
    Activations Density 0.228%

    No Known Activations