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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 10826
    Prev
    Next
    INDEX
    Explanations

    references to cold, hard truths or cold air

    oai_token-act-pair · gpt-3.5-turbo

    terms related to essential elements and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥ
    -0.82
    =-=-=-=-
    -0.75
    ãĥĥãĥī
    -0.72
    ãĤ¨ãĥ«
    -0.71
    =-=-=-=-=-=-=-=-
    -0.70
    BUS
    -0.69
    URA
    -0.68
    ²¾
    -0.67
    ãĤ¤
    -0.67
    izarre
    -0.66
    POSITIVE LOGITS
    nered
    0.99
    edly
    0.91
     (>
    0.84
     syndrome
    0.77
     (<
    0.75
     fallacy
    0.71
    ounters
    0.71
     approach
    0.71
    âĦ¢:
    0.70
    nings
    0.69
    Activations Density 0.477%

    No Known Activations