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. 8770
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data processing and analysis

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology related to scientific and medical processes

    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
     hesitated
    -0.66
     dodged
    -0.65
     enthusi
    -0.61
    iami
    -0.58
    WARN
    -0.58
    jew
    -0.58
    kell
    -0.57
     apologized
    -0.56
     kissed
    -0.56
     greeted
    -0.56
    POSITIVE LOGITS
     counterparts
    0.95
     counterpart
    0.80
     elsewhere
    0.74
     realities
    0.72
     ones
    0.71
     existing
    0.70
    existing
    0.70
    alogue
    0.62
     objectives
    0.61
     backdrop
    0.61
    Activations Density 0.702%

    No Known Activations