© 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. 9225
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases in all caps, identifying entities like names, places, and brands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "PH" and related terms

    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
    ãĥł
    -0.87
    hof
    -0.85
    ãĥĥ
    -0.83
    ãĤª
    -0.75
    ãĥ¼ãĤ¯
    -0.74
    eer
    -0.74
    eering
    -0.74
    éĹĺ
    -0.73
    eers
    -0.71
    case
    -0.71
    POSITIVE LOGITS
    OTO
    1.21
    OTOS
    1.05
    YS
    0.98
    antom
    0.98
    anthrop
    0.94
    PH
    0.91
    ippi
    0.89
    ONE
    0.88
    ysics
    0.85
    ONY
    0.85
    Activations Density 0.010%

    No Known Activations