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. 8-RES-JB
    6. 21342
    Prev
    Next
    INDEX
    Explanations

    phrases related to lessons, messages, and warnings

    oai_token-act-pair · gpt-3.5-turbo

    messages related to the importance of valuing friendships and community connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.82
    ItemTracker
    -0.76
     largeDownload
    -0.73
    mentioned
    -0.70
    cellaneous
    -0.69
    umbnails
    -0.67
    >:
    -0.66
     narration
    -0.64
    laughter
    -0.63
     mentions
    -0.63
    POSITIVE LOGITS
     realities
    0.75
     prevail
    0.74
     truly
    0.73
    equality
    0.71
     dangers
    0.71
     âī¡
    0.70
     compromises
    0.67
    cellence
    0.66
    ailability
    0.66
     sacrifices
    0.65
    Activations Density 0.731%

    No Known Activations