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. 4-RES-JB
    6. 12692
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'By' followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or processes

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

    No Comments

    Negative Logits
    uyomi
    -0.69
    nesota
    -0.64
    gaard
    -0.63
    oÄŁ
    -0.61
    wide
    -0.59
     edition
    -0.59
     awaited
    -0.58
    exist
    -0.58
     Edition
    -0.57
     awaiting
    -0.57
    POSITIVE LOGITS
     oneself
    0.76
    acles
    0.75
    olphin
    0.71
     yourself
    0.71
    ãĥ¼ãĥĨ
    0.71
    IDS
    0.66
    ACA
    0.65
     Yourself
    0.65
    PER
    0.64
    éŃĶ
    0.63
    Activations Density 0.160%

    No Known Activations