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. 10842
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of potential

    oai_token-act-pair · gpt-3.5-turbo

    references to potential or capability in various 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
    ching
    -0.75
    strap
    -0.73
    cloth
    -0.72
    chet
    -0.72
    cise
    -0.69
    men
    -0.69
    ogie
    -0.68
    ograph
    -0.68
    cipline
    -0.67
    ĪĴ
    -0.67
    POSITIVE LOGITS
    ities
    0.90
     usefulness
    0.86
    izons
    0.82
    ibilities
    0.81
     pitfalls
    0.80
     implications
    0.79
     hazards
    0.77
    atility
    0.76
     adversaries
    0.74
    externalActionCode
    0.73
    Activations Density 0.033%

    No Known Activations