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. 16509
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a unit of time (such as "a week or two") in the context of a duration or occurrence

    oai_token-act-pair · gpt-3.5-turbo

    references to a duration of time, specifically related to "one or two" instances

    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
    rim
    -0.68
    rays
    -0.67
     Vil
    -0.67
    UCT
    -0.64
    urated
    -0.63
    rams
    -0.63
    ursed
    -0.62
    orius
    -0.60
     Regions
    -0.60
    artments
    -0.59
    POSITIVE LOGITS
     depending
    0.81
     glance
    0.74
     ago
    0.73
     unlucky
    0.66
    depending
    0.64
     thereof
    0.64
     thereafter
    0.64
     glimpse
    0.63
     later
    0.62
     weren
    0.62
    Activations Density 0.035%

    No Known Activations