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. 1-RES-JB
    6. 9957
    Prev
    Next
    INDEX
    Explanations

    references to timelines

    oai_token-act-pair · gpt-3.5-turbo

    references to timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hammad
    -0.88
    iasis
    -0.86
    vasive
    -0.84
    ymph
    -0.81
    inence
    -0.79
    doms
    -0.78
    ateurs
    -0.77
    orous
    -0.76
    rieved
    -0.75
    raved
    -0.75
    POSITIVE LOGITS
     timeline
    1.24
     timelines
    1.11
     Timeline
    1.05
     timeframe
    0.81
     timetable
    0.80
     Miko
    0.79
     Coffin
    0.72
     wip
    0.70
     Chron
    0.70
     synopsis
    0.69
    Activations Density 0.006%

    No Known Activations