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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 14277
    Prev
    Next
    INDEX
    Explanations

    words related to drug policy, particularly focusing on the concept of decriminalization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the legalization and decriminalization of substances

    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
     Achilles
    -0.65
     Hills
    -0.65
     Preferred
    -0.64
    PAR
    -0.63
    quickShipAvailable
    -0.63
    gi
    -0.63
    lli
    -0.62
     Boh
    -0.62
    tem
    -0.62
     Madison
    -0.62
    POSITIVE LOGITS
     decriminal
    1.27
    ization
    1.05
    isation
    0.92
    ifiable
    0.91
    izing
    0.87
    ized
    0.86
    ised
    0.85
    ification
    0.85
    icity
    0.84
    ified
    0.80
    Activations Density 0.006%

    No Known Activations