© 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. 2-RES-JB
    11. 17100
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and organizations, particularly in a news context

    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
    ively
    -0.73
     pity
    -0.67
    iveness
    -0.65
    uncture
    -0.65
    ulse
    -0.65
     Akron
    -0.64
    orship
    -0.64
    skin
    -0.62
    esthetic
    -0.61
    saf
    -0.61
    POSITIVE LOGITS
    BER
    1.38
    LIN
    1.29
    GER
    1.14
    ertodd
    1.09
    RY
    1.05
    keley
    1.05
    EGIN
    0.99
    SU
    0.99
    ļéĨĴ
    0.97
    LAND
    0.96
    Activations Density 0.011%

    No Known Activations