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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 23219
    Prev
    Next
    INDEX
    Explanations

    phrases referring to something specific or highlighting a particular aspect

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¹ãĥĪ
    -0.88
    omo
    -0.81
    amia
    -0.72
    ©¶æ¥µ
    -0.70
     è£ıè¦ļéĨĴ
    -0.70
    raq
    -0.69
    ickets
    -0.68
    Ñĥ
    -0.68
    pots
    -0.66
    ãĥı
    -0.66
    POSITIVE LOGITS
     week
    0.95
     trope
    0.93
     guy
    0.83
     incarnation
    0.81
     year
    0.79
     month
    0.79
     installment
    0.78
     WEEK
    0.78
     weekend
    0.77
     latest
    0.77
    Activations Density 0.226%

    No Known Activations