© 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. 3-RES-JB
    11. 12915
    Prev
    Next
    INDEX
    Explanations

    mentions of entities or events associated with the name "Mar"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Mar" followed by a number or letter, likely indicating dates or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -1.13
    ħĭ
    -1.03
    é¾įå¥ij士
    -0.86
    anwhile
    -0.82
    ij士
    -0.77
    ngth
    -0.74
    hower
    -0.73
    uyomi
    -0.72
     tray
    -0.71
    culosis
    -0.70
    POSITIVE LOGITS
    riages
    1.06
    ried
    1.00
    ital
    1.00
    riage
    0.99
    lene
    0.94
    aqu
    0.92
    azz
    0.90
    vin
    0.88
    ice
    0.85
    iscal
    0.85
    Activations Density 0.016%

    No Known Activations