© 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. 7-RES-JB
    11. 4373
    Prev
    Next
    INDEX
    Explanations

    city or location names starting with "Mon"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "Mon" or its variations, indicating a focus on a specific entity or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Norn
    -0.85
    ACTED
    -0.75
    OHN
    -0.74
    FUL
    -0.74
    REE
    -0.72
    Reviewer
    -0.72
    æĸ¹
    -0.71
    enegger
    -0.69
    éĹĺ
    -0.69
    ONSORED
    -0.69
    POSITIVE LOGITS
    itored
    1.25
    olith
    1.18
    astery
    1.14
    stros
    1.12
    olithic
    1.10
    opoly
    1.08
    soon
    1.01
    roe
    1.01
    ograph
    1.00
    oton
    0.98
    Activations Density 0.019%

    No Known Activations