© 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. 4-RES-JB
    11. 1248
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations mentioned in the document, such as "Ipswich" and "Euclid Corridor Transportation Project."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places, events, or organizations

    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
    geon
    -0.90
    notes
    -0.83
    smanship
    -0.79
    stroke
    -0.74
    quished
    -0.72
    roller
    -0.71
    ifying
    -0.70
    enegger
    -0.68
    IFIC
    -0.68
    fman
    -0.68
    POSITIVE LOGITS
    ilon
    1.18
    neapolis
    0.81
    hire
    0.79
    odic
    0.75
    ãģĨ
    0.72
     Eps
    0.72
    hov
    0.72
    hin
    0.71
     Ips
    0.68
    adish
    0.68
    Activations Density 0.025%

    No Known Activations