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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 5678
    Prev
    Next
    INDEX
    Explanations

    proper names related to politics, especially focusing on a particular person named Malcolm Turnbull

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those related to Malcolm Turnbull

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rums
    -0.74
    spring
    -0.73
     payable
    -0.73
    BAT
    -0.72
    ngth
    -0.71
    sburgh
    -0.68
    mble
    -0.68
    arte
    -0.68
    ricular
    -0.67
     habitable
    -0.64
    POSITIVE LOGITS
     Turnbull
    1.13
    colm
    1.07
    sey
    1.01
     Malcolm
    0.86
     Tucker
    0.81
     Glad
    0.73
    iane
    0.72
     Fraser
    0.72
     Trudeau
    0.71
     Reed
    0.71
    Activations Density 0.014%

    No Known Activations