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. 10-RES-JB
    6. 17038
    Prev
    Next
    INDEX
    Explanations

    phrases related to helping and assisting others

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to individuals or groups in need or facing challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.69
    zeb
    -0.67
     Alive
    -0.66
     Slim
    -0.65
     carnage
    -0.65
     bloodshed
    -0.62
     convincing
    -0.62
    uphem
    -0.60
     manslaughter
    -0.57
     Mandal
    -0.56
    POSITIVE LOGITS
     might
    1.16
     may
    1.11
     otherwise
    1.09
     want
    1.05
     need
    1.01
    might
    0.99
     wish
    0.97
    want
    0.97
     wished
    0.96
     rely
    0.96
    Activations Density 0.213%

    No Known Activations