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. 14928
    Prev
    Next
    INDEX
    Explanations

    information related to personal or professional life events, such as marriages, career moves, and achievements

    oai_token-act-pair · gpt-3.5-turbo

    events related to family and relationships

    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
    weak
    -0.69
    ubis
    -0.68
     Warning
    -0.65
     accus
    -0.61
     Explan
    -0.59
     inaccurate
    -0.59
     IMAGES
    -0.59
    yip
    -0.59
    etermin
    -0.59
    len
    -0.59
    POSITIVE LOGITS
     renamed
    1.34
     thereafter
    1.24
     eventually
    1.18
     subsequently
    1.12
     became
    1.09
     Became
    1.07
     soon
    1.04
     promptly
    1.04
     gradually
    1.03
     proceeded
    0.99
    Activations Density 0.672%

    No Known Activations