© 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. 8-RES-JB
    11. 4144
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mar" followed by a variety of different suffixes or prefixes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.83
     tray
    -0.77
    ħĭ
    -0.75
    é¾įå¥ij士
    -0.71
    FUL
    -0.69
    代
    -0.67
    âĶģ
    -0.65
     depos
    -0.64
    edIn
    -0.63
    ãĤĮ
    -0.62
    POSITIVE LOGITS
    riages
    1.24
    ried
    1.10
    riage
    1.09
    ches
    1.07
    cell
    1.02
    chers
    0.99
    lene
    0.98
    ussia
    0.98
    ital
    0.97
    rying
    0.96
    Activations Density 0.019%

    No Known Activations