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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 23135
    Prev
    Next
    INDEX
    Explanations

    words related to physical or mental health issues, particularly focusing on symptoms like illness, ailments, aches, and discomfort

    oai_token-act-pair · gpt-3.5-turbo

    words related to health or issues affecting well-being

    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
    emort
    -0.89
     precincts
    -0.77
     fixme
    -0.72
    utenberg
    -0.71
     IDs
    -0.68
     FIG
    -0.68
     jams
    -0.67
    IDs
    -0.66
    codes
    -0.66
     sidx
    -0.66
    POSITIVE LOGITS
    otropic
    0.68
    bestos
    0.66
    herent
    0.64
     steroid
    0.63
     Leonardo
    0.63
    pit
    0.63
    raft
    0.62
    volent
    0.61
    nikov
    0.61
     Morsi
    0.61
    Activations Density 0.051%

    No Known Activations