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. 879
    Prev
    Next
    INDEX
    Explanations

    noun phrases referring to a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "this time" in relation to various topics

    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
     Others
    -0.71
    Others
    -0.67
    arine
    -0.65
    Alert
    -0.64
    quartered
    -0.64
    rt
    -0.62
    Synopsis
    -0.61
     Numerous
    -0.61
    alyses
    -0.60
    leground
    -0.59
    POSITIVE LOGITS
    phasis
    0.70
     Ame
    0.70
     however
    0.68
     kicker
    0.63
     lucky
    0.60
     emphasis
    0.60
     chances
    0.59
     instead
    0.58
    instead
    0.57
     Devon
    0.55
    Activations Density 0.260%

    No Known Activations