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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9972
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to the Vice President

    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
    ANC
    -0.69
     scrim
    -0.67
     ILCS
    -0.66
    banks
    -0.65
    é¾įå
    -0.65
     exting
    -0.63
    wcsstore
    -0.62
     plate
    -0.61
    aber
    -0.60
     fins
    -0.59
    POSITIVE LOGITS
     Biden
    1.01
     Lyndon
    0.77
     Marshal
    0.71
     Cheney
    0.70
    OTUS
    0.70
     Theodore
    0.70
     Pence
    0.70
    ial
    0.68
    president
    0.68
    Rah
    0.66
    Activations Density 0.028%

    No Known Activations