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. 10801
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'Smarter' and variations of the name 'Pablo Escobar'

    oai_token-act-pair · gpt-3.5-turbo

    words related to intelligence enhancement, particularly in the context of drug-related discussions

    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
     Pwr
    -0.74
    Quantity
    -0.70
    UME
    -0.69
    uge
    -0.63
    AMI
    -0.63
     Honour
    -0.62
    76561
    -0.62
    APD
    -0.61
    Mich
    -0.61
     Surviv
    -0.61
    POSITIVE LOGITS
    tyard
    1.04
    belt
    0.92
    arter
    0.84
    aneously
    0.83
    paren
    0.79
    tainment
    0.79
    finals
    0.79
    ners
    0.79
    arters
    0.77
    poon
    0.76
    Activations Density 0.009%

    No Known Activations