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. 19109
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific time of "midnight"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "midnight" in various contexts

    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
    glomer
    -0.74
    lde
    -0.73
    ī
    -0.72
    ophy
    -0.72
    Reviewer
    -0.71
    umni
    -0.71
     behav
    -0.70
    artments
    -0.69
    designed
    -0.69
    govern
    -0.68
    POSITIVE LOGITS
     EDT
    1.06
     EST
    1.04
     PST
    0.99
     PDT
    0.98
     CET
    0.98
     hours
    0.96
     ET
    0.93
     GMT
    0.93
     Monday
    0.90
     curfew
    0.90
    Activations Density 0.060%

    No Known Activations