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. 11-RES-JB
    6. 19609
    Prev
    Next
    INDEX
    Explanations

    keywords related to caring or concern for something or someone

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or care for people or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĪ
    -0.65
    jam
    -0.64
     captcha
    -0.59
     Milky
    -0.57
     Transcript
    -0.56
    Assembly
    -0.55
     Immunity
    -0.55
    UES
    -0.55
     simul
    -0.55
    oute
    -0.54
    POSITIVE LOGITS
     about
    1.33
     passionately
    1.22
     ABOUT
    1.18
    lessly
    1.14
     deeply
    1.10
    about
    1.00
     About
    0.98
     enough
    0.90
    About
    0.88
    lessness
    0.87
    Activations Density 0.029%

    No Known Activations