© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 12082
    Prev
    Next
    INDEX
    Explanations

    references to actions related to reducing or restricting something, especially pertaining to populations or groups

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cull" and related terms, often in the context of population control or management

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

    No Comments

    Negative Logits
    oshenko
    -0.85
    hemat
    -0.81
    nerg
    -0.78
    igma
    -0.73
     Harlem
    -0.69
    former
    -0.66
    cers
    -0.66
    Supporters
    -0.66
    chel
    -0.65
     Abdel
    -0.64
    POSITIVE LOGITS
     cull
    0.88
    ing
    0.81
    ebin
    0.78
    s
    0.78
    shire
    0.74
    obal
    0.74
    ed
    0.74
    anas
    0.72
    sburg
    0.69
    iard
    0.69
    Activations Density 0.022%

    No Known Activations