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. 6-RES-JB
    6. 6314
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "As is"

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that indicate commonality or general statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istries
    -1.04
    wa
    -0.68
    wu
    -0.67
    acements
    -0.67
     Dragons
    -0.66
    ynes
    -0.63
     Halls
    -0.63
    iard
    -0.63
    eering
    -0.62
    aukee
    -0.61
    POSITIVE LOGITS
     evidenced
    0.97
     usual
    0.85
    Downloadha
    0.76
     presently
    0.75
     evident
    0.74
     doubtless
    0.71
    CLASSIFIED
    0.67
     customary
    0.67
     plaus
    0.66
    Unix
    0.65
    Activations Density 0.028%

    No Known Activations