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. 6-RES-JB
    6. 17902
    Prev
    Next
    INDEX
    Explanations

    terms related to organized crime and corruption

    oai_token-act-pair · gpt-3.5-turbo

    references to organized crime and its various aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reys
    -0.76
    ths
    -0.73
    lease
    -0.72
    ï¸ı
    -0.71
    gets
    -0.70
    hner
    -0.69
    rendered
    -0.69
    PLIED
    -0.68
    qt
    -0.67
    gam
    -0.67
    POSITIVE LOGITS
    eering
    1.01
    izational
    0.97
    urally
    0.92
     organizing
    0.89
    arity
    0.86
     Parenthood
    0.86
     affili
    0.85
     organized
    0.82
     organising
    0.79
    eers
    0.76
    Activations Density 0.034%

    No Known Activations