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. 20210
    Prev
    Next
    INDEX
    Explanations

    locations, political parties, organizations, and sports teams

    oai_token-act-pair · gpt-3.5-turbo

    references to specific political entities and football teams

    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
     misdemeanor
    -0.82
     DUI
    -0.76
     nonprofits
    -0.75
     statewide
    -0.74
     Boone
    -0.73
     NAACP
    -0.73
     felony
    -0.71
     nonpartisan
    -0.71
     feds
    -0.70
     LAPD
    -0.70
    POSITIVE LOGITS
    alys
    0.93
    croft
    0.92
    ghai
    0.91
     recognise
    0.87
    avour
    0.85
    entin
    0.83
     learnt
    0.81
     analys
    0.80
    elling
    0.80
     Programme
    0.78
    Activations Density 0.713%

    No Known Activations