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. 15545
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological aspects such as origins, events, and logging

    oai_token-act-pair · gpt-3.5-turbo

    words associated with origins or sources of events

    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
    arent
    -0.62
     alleges
    -0.61
     lashes
    -0.60
     asserts
    -0.59
     contends
    -0.58
     Unsure
    -0.57
     expired
    -0.56
    soType
    -0.55
     clarification
    -0.55
     whine
    -0.55
    POSITIVE LOGITS
     these
    0.65
    isites
    0.62
    scription
    0.62
     carbohyd
    0.62
    ouched
    0.61
    entin
    0.60
     theirs
    0.60
    anamo
    0.59
    rafted
    0.58
     Ellison
    0.58
    Activations Density 1.029%

    No Known Activations