© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17835
    Prev
    Next
    INDEX
    Explanations

    references to legal infractions and violations

    oai_token-act-pair · gpt-3.5-turbo

    words related to infractions or violations of laws and codes

    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
    lining
    -0.70
    soDeliveryDate
    -0.66
    kn
    -0.65
    building
    -0.65
    ned
    -0.65
    nas
    -0.64
     wills
    -0.64
    itability
    -0.63
    ning
    -0.62
    anas
    -0.61
    POSITIVE LOGITS
    raction
    0.97
    ractions
    0.88
     Citation
    0.83
    oons
    0.69
     Extras
    0.69
     Forbidden
    0.68
     citation
    0.67
     Jagu
    0.67
    terness
    0.67
    ij士
    0.67
    Activations Density 0.016%

    No Known Activations