© 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. 11490
    Prev
    Next
    INDEX
    Explanations

    numerical quantities related to time and count

    oai_token-act-pair · gpt-3.5-turbo

    references to structured sequences or cycles in events or actions

    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
    Sov
    -0.71
    adem
    -0.65
    mobi
    -0.65
    NetMessage
    -0.64
     consortium
    -0.64
    arty
    -0.63
    egu
    -0.61
    umbn
    -0.60
    ortium
    -0.60
    culosis
    -0.58
    POSITIVE LOGITS
     thereafter
    1.06
     thereof
    1.05
     of
    0.88
     individually
    0.86
     preceding
    0.81
     consecut
    0.80
     onwards
    0.78
     elapsed
    0.75
     imaginable
    0.73
     spent
    0.72
    Activations Density 0.185%

    No Known Activations