© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20477
    Prev
    Next
    INDEX
    Explanations

    words related to drugs, criminal activities, and legal terminology

    oai_token-act-pair · gpt-3.5-turbo

    the specific term "Het" which appears frequently in various contexts

    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
    BuyableInstoreAndOnline
    -0.77
     chilled
    -0.63
    conservancy
    -0.62
     convol
    -0.61
     viewing
    -0.60
    enhagen
    -0.59
    BACK
    -0.59
    reverse
    -0.59
     equ
    -0.58
    ortium
    -0.57
    POSITIVE LOGITS
    het
    1.23
    ype
    1.11
    amines
    1.10
    icals
    1.09
    ty
    1.05
    rette
    1.02
    oric
    1.00
    orically
    0.99
    eless
    0.98
    te
    0.98
    Activations Density 0.011%

    No Known Activations