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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4099
    Prev
    Next
    INDEX
    Explanations

    phrases related to city councils and government processes

    oai_token-act-pair · gpt-3.5-turbo

    references to city council activities and decisions

    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
    ãĤ¯
    -0.84
    ichen
    -0.79
    aphael
    -0.76
    ylan
    -0.75
    xes
    -0.73
    ures
    -0.73
    Euro
    -0.72
    legged
    -0.71
    asia
    -0.71
    ifix
    -0.71
    POSITIVE LOGITS
     superintendent
    0.96
     commissioners
    0.92
     sheriff
    0.92
     COUNTY
    0.91
    uliffe
    0.87
     dispatcher
    0.86
     County
    0.84
     Corrections
    0.84
     homeowner
    0.84
    VILLE
    0.83
    Activations Density 1.515%

    No Known Activations