© 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. 3-RES-JB
    6. 12337
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal activities or controversial issues like piracy, prostitution, and circumcision

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illegal activities and controversial social issues

    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
    Lear
    -0.71
    Animal
    -0.69
    abase
    -0.69
    nant
    -0.65
    leon
    -0.65
    TAIN
    -0.65
    estones
    -0.65
     <+
    -0.64
    izen
    -0.64
     CFR
    -0.63
    POSITIVE LOGITS
     prevention
    0.94
     cessation
    0.83
     awareness
    0.82
    iferation
    0.81
    anship
    0.79
     enforcement
    0.76
     efforts
    0.75
     spree
    0.73
     techniques
    0.73
     entrepreneurship
    0.73
    Activations Density 0.070%

    No Known Activations