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. 4-RES-JB
    6. 9953
    Prev
    Next
    INDEX
    Explanations

    mentions of the drug "cocaine."

    oai_token-act-pair · gpt-3.5-turbo

    references to cocaine 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
    hof
    -0.84
    å§«
    -0.75
    yll
    -0.73
     Arbor
    -0.71
    Bird
    -0.70
    igating
    -0.70
     Worcester
    -0.69
    lich
    -0.67
    soType
    -0.67
    inen
    -0.66
    POSITIVE LOGITS
     cocaine
    1.15
     residue
    1.04
     addiction
    0.89
     overdose
    0.86
     addicts
    0.83
     cartels
    0.83
     overdoses
    0.82
     methamphetamine
    0.81
     sulf
    0.79
    stasy
    0.79
    Activations Density 0.014%

    No Known Activations