© 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. 1083
    Prev
    Next
    INDEX
    Explanations

    dates, especially focusing on the month of July

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months and years

    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
    natureconservancy
    -0.73
    vs
    -0.69
    dh
    -0.62
    terness
    -0.62
    WF
    -0.62
    MJ
    -0.61
    jc
    -0.58
    rh
    -0.58
    esc
    -0.57
     insider
    -0.55
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    0.71
    ))))
    0.70
     (%)
    0.70
     =================================
    0.67
     ðŁĻĤ
    0.67
     Turnbull
    0.66
    ÙĦ
    0.65
     =================================================================
    0.64
     ($)
    0.64
     Allaah
    0.63
    Activations Density 0.028%

    No Known Activations