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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 6035
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    prominent political figures and mention them within a political context

    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
    Miami
    -0.93
    ¥µ
    -0.93
    Denver
    -0.92
     Grateful
    -0.90
    Atlanta
    -0.89
    Kansas
    -0.88
    Philadelphia
    -0.88
    Detroit
    -0.87
     honoring
    -0.86
    Chicago
    -0.85
    POSITIVE LOGITS
     MPs
    1.17
    colour
    1.15
     apologised
    1.13
     Miliband
    1.10
     emphas
    1.08
     Turnbull
    1.07
     councillors
    1.07
     recognise
    1.07
     centre
    1.06
     Nigel
    1.05
    Activations Density 0.302%

    No Known Activations