© 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. 4-RES-JB
    11. 15263
    Prev
    Next
    INDEX
    Explanations

    words related to city councils and their activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related 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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zsche
    -0.84
    ihadi
    -0.81
     Britons
    -0.76
    nikov
    -0.74
    ipolar
    -0.73
    British
    -0.73
    γ
    -0.71
    ãĥ¼ãĥĨ
    -0.71
     tonnes
    -0.71
    alys
    -0.70
    POSITIVE LOGITS
     district
    0.93
     Legislature
    0.93
     ordinance
    0.89
     districts
    0.87
     commissioners
    0.85
     adjourn
    0.84
    itol
    0.83
     nonprofits
    0.83
     ordinances
    0.81
     statewide
    0.81
    Activations Density 0.250%

    No Known Activations