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. 9-RES-JB
    6. 20999
    Prev
    Next
    INDEX
    Explanations

    the latest news updates related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to current news updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wright
    -0.86
    shared
    -0.79
    xual
    -0.75
    ribed
    -0.69
    SPONSORED
    -0.68
    ractor
    -0.68
    committee
    -0.67
    phy
    -0.67
    minist
    -0.66
    apist
    -0.66
    POSITIVE LOGITS
     developments
    0.98
     arrivals
    0.97
     incarnation
    0.89
     iteration
    0.85
     headlines
    0.83
     updates
    0.82
     installment
    0.80
     edition
    0.80
     Updates
    0.78
     rumours
    0.77
    Activations Density 0.036%

    No Known Activations