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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15242
    Prev
    Next
    INDEX
    Explanations

    words related to immigration and materiality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to immigration

    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
    DragonMagazine
    -0.91
    uyomi
    -0.90
    sonian
    -0.84
    ¶ħ
    -0.84
    ģĸ
    -0.83
    姫
    -0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    ļéĨĴ
    -0.77
    BOOK
    -0.76
    é¾įå¥ij士
    -0.73
    POSITIVE LOGITS
    igrated
    1.20
    ovable
    1.14
    obile
    1.11
    aterial
    1.10
    igrants
    1.04
    igr
    1.01
    igration
    0.95
    itates
    0.94
    igrate
    0.91
    itated
    0.91
    Activations Density 0.006%

    No Known Activations