Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10012
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of "long" in a temporal or spatial context

    oai_token-act-pair · gpt-3.5-turbo

    references to prolonged durations or time spent on activities

    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
    Tro
    -0.75
    artisan
    -0.68
    eanor
    -0.66
    alle
    -0.66
     Cosponsors
    -0.65
    ery
    -0.65
    pered
    -0.63
     Coordinator
    -0.62
    mosp
    -0.61
    iquette
    -0.61
    POSITIVE LOGITS
     periods
    1.23
    term
    0.98
     stretches
    0.92
    itud
    0.91
    duration
    0.89
     continu
    0.87
     duration
    0.85
     (>
    0.85
    lasting
    0.83
    Distance
    0.83
    Activations Density 0.042%

    No Known Activations