© 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. 7174
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to places or objects that contain the syllable "mo"

    oai_token-act-pair · gpt-3.5-turbo

    suffixes or word parts that suggest pluralization or action in various contexts

    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
    ĪĴ
    -1.11
    İĭ
    -0.82
    Ö¼
    -0.76
    ©¶æ
    -0.73
    blogspot
    -0.67
     BIG
    -0.66
     stroke
    -0.65
    ä¸ī
    -0.63
     HDL
    -0.63
     prelim
    -0.62
    POSITIVE LOGITS
    uddin
    0.77
    ghan
    0.73
    heit
    0.72
    shots
    0.71
    arts
    0.70
    annel
    0.69
    east
    0.69
    erella
    0.68
    nels
    0.67
    iter
    0.67
    Activations Density 0.146%

    No Known Activations