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. 9558
    Prev
    Next
    INDEX
    Explanations

    time-related events such as weekdays, months, and years

    oai_token-act-pair · gpt-3.5-turbo

    references to recent events and timeframes

    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
    arta
    -0.63
     parap
    -0.61
     contiguous
    -0.61
     ak
    -0.60
     behaves
    -0.59
     preserves
    -0.59
    erate
    -0.58
     prefers
    -0.58
    anium
    -0.58
    atio
    -0.57
    POSITIVE LOGITS
     when
    1.01
    when
    0.95
     evidenced
    0.68
     unveiling
    0.67
     evening
    0.66
     involving
    0.66
     dawn
    0.66
     morning
    0.66
     regarding
    0.65
     announcing
    0.65
    Activations Density 0.308%

    No Known Activations