© 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. 5676
    Prev
    Next
    INDEX
    Explanations

    names or words containing "Hem"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "Hem" and related terms

    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
    ãģį
    -0.73
     AVG
    -0.73
    CLASSIFIED
    -0.72
    0000
    -0.68
    holder
    -0.65
    0000000
    -0.65
    ECTION
    -0.62
    çĶŁ
    -0.61
     Cyprus
    -0.61
     Barron
    -0.61
    POSITIVE LOGITS
    oglobin
    1.25
    ming
    1.14
    isphere
    1.02
    isp
    0.99
    odynamic
    0.98
    odynamics
    0.96
    mitt
    0.95
    ophon
    0.95
    sworth
    0.94
    odynam
    0.93
    Activations Density 0.007%

    No Known Activations