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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12398
    Prev
    Next
    INDEX
    Explanations

    references to specific political parties and individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political parties and their officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aturation
    -0.83
    sis
    -0.80
    ĸļ
    -0.79
     Bezos
    -0.77
    iceps
    -0.71
    atur
    -0.68
    ous
    -0.67
    ulous
    -0.67
    orer
    -0.67
    orage
    -0.66
    POSITIVE LOGITS
     Gael
    1.05
     Ministers
    0.95
     parliament
    0.92
     councillors
    0.90
     MPs
    0.89
     Confederation
    0.88
     Commissioners
    0.87
     ministerial
    0.87
     Parliamentary
    0.85
     Examiner
    0.85
    Activations Density 0.084%

    No Known Activations