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. 6-RES-JB
    6. 4938
    Prev
    Next
    INDEX
    Explanations

    events happening on consecutive days

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "the next day."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfocusedRange
    -0.84
    pmwiki
    -0.72
    otto
    -0.65
     misuse
    -0.64
    acus
    -0.64
    overe
    -0.62
    pires
    -0.61
    ocker
    -0.61
     fixme
    -0.60
    pol
    -0.60
    POSITIVE LOGITS
     when
    0.70
    aneously
    0.70
    orate
    0.66
    imester
    0.64
    ghan
    0.64
    cation
    0.63
    .—
    0.62
    oya
    0.61
    large
    0.61
     commute
    0.61
    Activations Density 0.044%

    No Known Activations