© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 24416
    Prev
    Next
    INDEX
    Explanations

    references to the drug ketamine

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ketamine and its effects

    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
    IBLE
    -0.80
    ãģĦ
    -0.76
     Strauss
    -0.75
     Directorate
    -0.75
    ãģĨ
    -0.75
     Tyson
    -0.75
    ãģį
    -0.74
    ATTLE
    -0.73
     Ago
    -0.73
     Forbidden
    -0.71
    POSITIVE LOGITS
    tering
    1.00
    ket
    0.93
    amine
    0.91
    ty
    0.89
    ropolis
    0.89
    rieg
    0.88
    eers
    0.88
    kered
    0.84
    osis
    0.82
    arus
    0.81
    Activations Density 0.015%

    No Known Activations