© 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. 2-RES-JB
    11. 22045
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, especially names of cities or countries

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.87
    âĶĢâĶĢâĶĢâĶĢ
    -0.85
    anooga
    -0.81
    rosse
    -0.81
    س
    -0.77
    operative
    -0.76
    76561
    -0.76
    ~~~~~~~~~~~~~~~~
    -0.75
    iov
    -0.74
    OTS
    -0.74
    POSITIVE LOGITS
    uggets
    0.96
    iferation
    0.85
    guyen
    0.83
    usra
    0.78
    issan
    0.74
    emonic
    0.74
    swer
    0.74
    vironment
    0.73
    IGH
    0.72
    iece
    0.71
    Activations Density 0.041%

    No Known Activations