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. 7-RES-JB
    6. 3484
    Prev
    Next
    INDEX
    Explanations

    phrases related to the unfolding or development of events or stories

    oai_token-act-pair · gpt-3.5-turbo

    references to events or processes that are developing or evolving over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --+
    -0.69
    ifier
    -0.69
    vation
    -0.69
    ena
    -0.69
    gment
    -0.67
    anguage
    -0.66
    Reference
    -0.66
    arcity
    -0.66
    Vs
    -0.64
    iphate
    -0.63
    POSITIVE LOGITS
     unfold
    1.02
     unfolding
    0.90
     intertw
    0.86
     intertwined
    0.82
     unfolded
    0.78
     unfolds
    0.77
    Ire
    0.76
    olitics
    0.74
     embroiled
    0.73
     complexities
    0.73
    Activations Density 0.137%

    No Known Activations