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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 5091
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific place or person named 'Ran'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ran" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GMT
    -0.66
    ij士
    -0.65
    ĨĴ
    -0.62
     minors
    -0.62
    ãĢIJ
    -0.62
    £ı
    -0.61
     Holden
    -0.60
     subp
    -0.59
     magnitude
    -0.59
     favors
    -0.58
    POSITIVE LOGITS
    igans
    1.11
    igan
    1.02
    vier
    1.00
    quez
    0.98
    zan
    0.92
    coe
    0.89
    ran
    0.86
    hari
    0.85
    fo
    0.85
    egal
    0.83
    Activations Density 0.010%

    No Known Activations