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. 0-RES-JB
    6. 20719
    Prev
    Next
    INDEX
    Explanations

    terminology related to power outages and media blackouts

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with power outages and media restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Path
    -0.76
    etts
    -0.74
    gnu
    -0.73
    ptr
    -0.68
     Ulster
    -0.68
    meat
    -0.66
     paths
    -0.66
    eem
    -0.66
    kind
    -0.66
    icester
    -0.64
    POSITIVE LOGITS
     blackout
    4.07
     outage
    1.70
     gag
    1.34
     curfew
    1.27
     haze
    1.20
     lockout
    1.20
     coma
    1.11
    NPR
    1.08
    nesia
    0.97
     downtime
    0.95
    Activations Density 0.041%

    No Known Activations