Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8481
    Prev
    Next
    INDEX
    Explanations

    Spanish words related to law enforcement and judicial processes

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to quantity and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Asian
    -0.82
    APH
    -0.80
    things
    -0.79
    setting
    -0.78
    ratch
    -0.77
    VW
    -0.77
    arians
    -0.77
    British
    -0.76
    external
    -0.75
    athi
    -0.74
    POSITIVE LOGITS
     los
    1.28
     la
    1.22
     este
    1.19
     las
    1.13
     les
    1.11
     nos
    1.07
     sus
    1.05
     tu
    0.99
     é
    0.98
     si
    0.97
    Activations Density 0.057%

    No Known Activations