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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21029
    Prev
    Next
    INDEX
    Explanations

    proper nouns often related to news articles or current events

    oai_token-act-pair · gpt-3.5-turbo

    the word "That" in various contexts

    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
    hops
    -0.88
    ¶ħ
    -0.87
     dstg
    -0.79
    hips
    -0.79
    paces
    -0.78
    rypt
    -0.76
    20439
    -0.75
    natureconservancy
    -0.74
    oby
    -0.73
    ccoli
    -0.73
    POSITIVE LOGITS
    's
    1.21
     includes
    1.06
     hasn
    1.04
     translates
    1.00
     prompted
    0.97
     doesn
    0.95
     begs
    0.94
     brings
    0.93
     wasn
    0.91
    cher
    0.91
    Activations Density 0.095%

    No Known Activations