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. 7-RES-JB
    6. 13285
    Prev
    Next
    INDEX
    Explanations

    command-like sentences or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey action or decision-making in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zbollah
    -0.76
    ahime
    -0.65
    ampions
    -0.62
    adium
    -0.61
     Comprehensive
    -0.60
    ularity
    -0.59
    ishable
    -0.59
     Doomsday
    -0.58
     UNITED
    -0.57
    Brexit
    -0.57
    POSITIVE LOGITS
    upon
    0.82
    Later
    0.73
     then
    0.72
     later
    0.72
     reluctantly
    0.69
     instructed
    0.69
     promptly
    0.69
     startled
    0.65
     astonished
    0.64
     hurried
    0.63
    Activations Density 1.004%

    No Known Activations