© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 22340
    Prev
    Next
    INDEX
    Explanations

    references to municipal levels or aspects in documents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to municipal governance and administration

    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
    clips
    -0.76
    witch
    -0.68
     Secrets
    -0.67
    fy
    -0.67
     Clip
    -0.67
     Frames
    -0.65
     Decay
    -0.64
    clip
    -0.64
     Jake
    -0.63
     CTRL
    -0.62
    POSITIVE LOGITS
     municipal
    3.50
     Municipal
    2.75
    unicip
    2.39
     municipality
    2.34
     municipalities
    2.26
     municip
    2.23
     Municip
    2.01
     mayoral
    1.79
     provincial
    1.72
     civic
    1.68
    Activations Density 0.019%

    No Known Activations