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. 2-RES-JB
    6. 8535
    Prev
    Next
    INDEX
    Explanations

    words related to actions or states of seeking, desiring, and taking pleasure in something

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and past participles related to actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilogy
    -0.69
     notebook
    -0.66
    sen
    -0.62
    ppard
    -0.60
    street
    -0.59
     Aerospace
    -0.58
    clerosis
    -0.57
     Ellison
    -0.57
    shr
    -0.57
    supp
    -0.57
    POSITIVE LOGITS
    ishes
    0.91
     Royale
    0.88
    »Ĵ
    0.83
    ishing
    0.78
    ãĤ¤ãĥĪ
    0.78
    ,,,,,,,,
    0.78
    ISH
    0.77
    ishment
    0.76
     Gamb
    0.74
    nesses
    0.73
    Activations Density 0.015%

    No Known Activations