© 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. 10-RES-JB
    11. 3032
    Prev
    Next
    INDEX
    Explanations

    terms related to specific districts or locations, particularly those denoted by the abbreviation "SE"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "SE" and "SW" as they relate to transportation services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dismant
    -0.70
    ua
    -0.69
    lessly
    -0.69
    staking
    -0.68
    aults
    -0.68
    istics
    -0.67
     inacc
    -0.66
    ocrats
    -0.66
    sei
    -0.66
    ongyang
    -0.66
    POSITIVE LOGITS
    IFT
    1.22
    IU
    1.20
    ARCH
    1.08
    ATTLE
    1.05
    TOR
    0.98
    VEN
    0.97
    SL
    0.90
    ITCH
    0.89
    ANA
    0.87
    SEA
    0.86
    Activations Density 0.024%

    No Known Activations