Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10484
    Prev
    Next
    INDEX
    Explanations

    amphetamine and related drugs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to amphetamines and other illicit drugs

    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
    earth
    -0.83
    elong
    -0.80
    Earth
    -0.77
    lying
    -0.75
    soType
    -0.71
    LOC
    -0.70
    laus
    -0.70
     Vec
    -0.68
    Pont
    -0.67
    ghai
    -0.65
    POSITIVE LOGITS
    stasy
    1.21
    amphetamine
    1.10
    hetamine
    1.08
     cocaine
    0.97
     methamphetamine
    0.86
     addicts
    0.84
     ecstasy
    0.84
     overdoses
    0.83
    amines
    0.82
     addict
    0.82
    Activations Density 0.015%

    No Known Activations