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. 4-RES-JB
    6. 5885
    Prev
    Next
    INDEX
    Explanations

    phrases related to making information publicly available

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of public accessibility or availability of information

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

    No Comments

    Negative Logits
    ophy
    -0.73
     Cherry
    -0.69
     Huntington
    -0.66
    outer
    -0.65
     Origin
    -0.65
    ategy
    -0.65
     Goo
    -0.65
    ebus
    -0.63
     hoops
    -0.63
    anky
    -0.63
    POSITIVE LOGITS
    Discover
    0.75
    raq
    0.72
    PDATE
    0.70
    =>
    0.68
    lishes
    0.67
    Reloaded
    0.67
    ãĤī
    0.65
    Republic
    0.65
    UTC
    0.65
    Keefe
    0.65
    Activations Density 0.048%

    No Known Activations