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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    6. 4387
    Prev
    Next
    INDEX
    Explanations

    words related to prescription drugs and medications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to addiction and prescription medications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Phys
    -0.72
    549
    -0.68
    code
    -0.65
    EG
    -0.64
     joint
    -0.64
    lier
    -0.63
    PT
    -0.62
     NIC
    -0.62
    Physical
    -0.61
    TX
    -0.61
    POSITIVE LOGITS
    poons
    1.48
    ervatives
    1.46
    paces
    1.37
    mith
    1.33
    aurus
    1.32
    hip
    1.25
    uggest
    1.25
    ervative
    1.24
    poon
    1.23
    hips
    1.22
    Activations Density 0.146%

    No Known Activations