© 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. 4-RES-JB
    11. 22075
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or statements indicating importance or relevance

    oai_token-act-pair · gpt-3.5-turbo

    patterns involving the phrase "that’s" or similar expressions

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

    No Comments

    Negative Logits
     carts
    -0.71
    izen
    -0.67
     jails
    -0.65
    prus
    -0.64
     recovery
    -0.64
     Wit
    -0.62
     Rag
    -0.59
     Travels
    -0.59
     produ
    -0.59
    perty
    -0.58
    POSITIVE LOGITS
    º
    0.95
    ¹
    0.93
    ®
    0.81
    £
    0.77
    soType
    0.76
    certain
    0.76
    acca
    0.75
    esta
    0.74
    âĢķ
    0.74
    Ĵ
    0.73
    Activations Density 0.127%

    No Known Activations