© 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. 20782
    Prev
    Next
    INDEX
    Explanations

    references to social welfare programs and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and programs related to welfare and assistance

    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
    é¾įå
    -0.80
    acters
    -0.78
    ãĥĦ
    -0.74
    ï¸
    -0.73
    Downloadha
    -0.73
    DragonMagazine
    -0.70
    */(
    -0.68
    witz
    -0.67
    ãĤ°
    -0.67
    à©
    -0.67
    POSITIVE LOGITS
    entric
    1.05
    trl
    1.01
    ontent
    0.97
    HAEL
    0.96
    LES
    0.95
    ALLY
    0.94
    onduct
    0.92
    ENSE
    0.90
    olor
    0.89
    ULT
    0.85
    Activations Density 0.006%

    No Known Activations