© 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. 4907
    Prev
    Next
    INDEX
    Explanations

    terms related to specific technology or product names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "X" 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
    getic
    -0.80
    kson
    -0.75
    inally
    -0.75
     stru
    -0.73
    enegger
    -0.72
    assetsadobe
    -0.72
    м
    -0.71
     Pru
    -0.70
     à¤
    -0.67
     respons
    -0.67
    POSITIVE LOGITS
    avier
    1.18
    peria
    1.10
    cellence
    1.07
    III
    1.00
    ML
    0.98
    posed
    0.96
    BOX
    0.95
    odus
    0.95
    ternal
    0.88
    IX
    0.88
    Activations Density 0.025%

    No Known Activations