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. 21008
    Prev
    Next
    INDEX
    Explanations

    words related to illegal drugs, particularly 'narco'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of narcotics or drug-related topics

    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
     GOODMAN
    -0.72
    Subject
    -0.70
     horm
    -0.68
     Skydragon
    -0.67
     Subjects
    -0.65
    lihood
    -0.65
     HELL
    -0.63
     thirds
    -0.62
    owship
    -0.62
     fet
    -0.62
    POSITIVE LOGITS
    xon
    1.21
    ffee
    1.15
    zzi
    1.02
    cephal
    1.01
    oldown
    0.97
    operation
    0.94
    atl
    0.94
    ppy
    0.92
    asters
    0.92
    operative
    0.91
    Activations Density 0.016%

    No Known Activations