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. 6-RES-JB
    6. 21424
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Hal"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Hal" mentioned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģķ
    -0.82
    URES
    -0.80
    é¾įå¥ij士
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.73
    æĸ¹
    -0.72
     nomine
    -0.72
    URE
    -0.70
    ãģį
    -0.67
    âĶģ
    -0.67
    çĶŁ
    -0.67
    POSITIVE LOGITS
    ftime
    1.19
    ifax
    1.14
    tering
    1.09
    iday
    1.08
    ibur
    0.99
    ogen
    0.97
    ocaust
    0.94
    ter
    0.92
    ving
    0.92
    pless
    0.91
    Activations Density 0.016%

    No Known Activations