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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5281
    Prev
    Next
    INDEX
    Explanations

    references to roads and their conditions, such as building, upgrading, accessing, or closing them

    oai_token-act-pair · gpt-3.5-turbo

    references to roads and their conditions

    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
    ividual
    -0.86
    arians
    -0.77
    ority
    -0.76
    rator
    -0.71
     Wong
    -0.71
    yip
    -0.71
    andum
    -0.68
    iaries
    -0.67
    ucket
    -0.67
    illian
    -0.66
    POSITIVE LOGITS
    ways
    1.25
    blocks
    1.12
     roads
    1.05
     Roads
    0.99
     highways
    0.97
    block
    0.96
     arteries
    0.95
    road
    0.94
    side
    0.94
    lane
    0.89
    Activations Density 0.025%

    No Known Activations