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. 2-RES-JB
    6. 16968
    Prev
    Next
    INDEX
    Explanations

    words related to decriminalization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the decriminalization of substances or activities

    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
    PAR
    -0.64
    lli
    -0.64
     OW
    -0.63
     Achilles
    -0.62
    tem
    -0.62
    sch
    -0.62
    hare
    -0.61
    lists
    -0.60
     Preferred
    -0.60
    gi
    -0.60
    POSITIVE LOGITS
     decriminal
    1.33
    ization
    1.01
    izont
    0.87
    isation
    0.84
    izing
    0.82
    ification
    0.82
     legalization
    0.81
    ifiable
    0.79
    ized
    0.78
    ising
    0.78
    Activations Density 0.003%

    No Known Activations