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. 10-RES-JB
    6. 3971
    Prev
    Next
    INDEX
    Explanations

    patterns related to data collection or gathering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gathering or acquiring information and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.64
    witz
    -0.63
    English
    -0.61
    minent
    -0.61
    lease
    -0.60
     Kardashian
    -0.59
    igmat
    -0.59
    ordering
    -0.57
     wrench
    -0.57
    mia
    -0.56
    POSITIVE LOGITS
    ibles
    1.00
     signatures
    0.99
    ivist
    0.94
    ively
    0.89
     dust
    0.88
    ennial
    0.87
     royalties
    0.84
    ivism
    0.83
    STON
    0.82
     dues
    0.78
    Activations Density 0.040%

    No Known Activations