© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 5603
    Prev
    Next
    INDEX
    Explanations

    words related to the city or place called "Worcester"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Wor" and its variants, indicating a focus on specific locations or names associated with that term

    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
    ividual
    -0.93
    anwhile
    -0.89
    uyomi
    -0.80
    ocracy
    -0.78
    ocratic
    -0.77
    ocene
    -0.74
    xual
    -0.73
     Democr
    -0.72
     holiest
    -0.72
    insula
    -0.72
    POSITIVE LOGITS
     Wor
    0.99
    rier
    0.92
    ried
    0.91
    risome
    0.91
    riers
    0.88
    rast
    0.80
    cester
    0.77
    rington
    0.76
    rim
    0.74
    rell
    0.74
    Activations Density 0.011%

    No Known Activations