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. 3470
    Prev
    Next
    INDEX
    Explanations

    specific references to weeks and rankings in a sports-related context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific weeks in a timeline or schedule

    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
    åĤ
    -0.65
     lum
    -0.64
    itars
    -0.64
    awei
    -0.61
     Kush
    -0.60
     precip
    -0.59
    Frameworks
    -0.58
    ithub
    -0.57
     chloride
    -0.56
    omething
    -0.56
    POSITIVE LOGITS
    days
    1.35
    night
    1.10
    DAY
    1.09
    lies
    1.02
    ends
    0.89
    day
    0.86
    aday
    0.83
    stop
    0.78
    liness
    0.77
    hof
    0.77
    Activations Density 0.056%

    No Known Activations