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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2752
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and organizational procedures

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may indicate specific operations or categories in a text

    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
     sucker
    -0.91
     piled
    -0.83
     damned
    -0.82
     imperson
    -0.78
     guy
    -0.77
     cheering
    -0.77
     whiff
    -0.76
     sprawling
    -0.76
     jammed
    -0.75
     tangled
    -0.73
    POSITIVE LOGITS
     Additionally
    1.17
    âĢ
    1.11
    âĢł
    1.10
     Therefore
    1.05
    Additionally
    1.05
    Based
    1.03
    Sources
    1.02
     However
    1.02
    Therefore
    1.02
     Ibid
    1.01
    Activations Density 0.244%

    No Known Activations