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. 8826
    Prev
    Next
    INDEX
    Explanations

    phrases related to a collection of various items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the word "all" used in various contexts

    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
    hz
    -0.75
    ichen
    -0.74
    hap
    -0.72
    atro
    -0.71
    atur
    -0.69
    atre
    -0.68
    icion
    -0.68
    culosis
    -0.67
    bor
    -0.66
    estamp
    -0.66
    POSITIVE LOGITS
    ocating
    1.15
    uding
    1.10
     kinds
    1.02
    iances
    0.99
     sorts
    0.98
    igators
    0.93
    owing
    0.91
    usions
    0.91
    ocated
    0.83
    ocations
    0.83
    Activations Density 0.072%

    No Known Activations