© 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. 10-RES-JB
    11. 12822
    Prev
    Next
    INDEX
    Explanations

    mentions of rules, regulations, violations, and associated penalties or punishments

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to legal violations and penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    optim
    -0.78
     Miracle
    -0.69
    wow
    -0.67
    ween
    -0.67
    Beaut
    -0.66
    pheus
    -0.66
    NetMessage
    -0.65
    bits
    -0.63
    akes
    -0.63
    Perfect
    -0.63
    POSITIVE LOGITS
     penalties
    1.63
     punishment
    1.53
     fines
    1.51
     punishments
    1.50
     penalty
    1.49
     reprim
    1.48
     fined
    1.44
     expulsion
    1.38
     imprisonment
    1.37
     jail
    1.37
    Activations Density 0.383%

    No Known Activations