© 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. 23537
    Prev
    Next
    INDEX
    Explanations

    references to a specific place or company named "Canton"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Cant" and its variations, indicating a focus on related entities or concepts

    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
    vernment
    -0.83
    CVE
    -0.80
    ãģį
    -0.79
    Reviewer
    -0.75
    æł
    -0.71
    ¯¯¯¯¯¯¯¯
    -0.70
    ously
    -0.67
    gnu
    -0.66
    issance
    -0.66
    ãģ®é
    -0.66
    POSITIVE LOGITS
    illon
    1.21
    rell
    1.17
    onso
    1.04
    een
    1.03
    rip
    0.93
    inas
    0.93
    aign
    0.90
    ina
    0.88
    lest
    0.87
    aleb
    0.87
    Activations Density 0.034%

    No Known Activations