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. 7-RES-JB
    6. 562
    Prev
    Next
    INDEX
    Explanations

    proper nouns, possibly related to locations or people

    oai_token-act-pair · gpt-3.5-turbo

    context related to city governance and local events

    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
     analys
    -0.98
     analyse
    -0.88
     realise
    -0.85
     realised
    -0.85
     scept
    -0.85
     maths
    -0.83
     fulfil
    -0.83
     analysed
    -0.82
     ageing
    -0.77
     epist
    -0.73
    POSITIVE LOGITS
     statewide
    1.18
     COUNTY
    1.15
    unicip
    1.04
    Mayor
    1.04
     Spokane
    0.96
     sidewalks
    0.95
     Oregon
    0.94
     zoning
    0.94
     Parks
    0.94
     homeowner
    0.93
    Activations Density 2.125%

    No Known Activations