© 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. 6704
    Prev
    Next
    INDEX
    Explanations

    phrases related to violating laws, rules, or standards

    oai_token-act-pair · gpt-3.5-turbo

    references to violations of laws and constitutional rights

    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
    iris
    -0.73
    bang
    -0.72
    enhagen
    -0.71
    hin
    -0.70
    rising
    -0.68
    naissance
    -0.67
    uilding
    -0.62
    rowth
    -0.61
    ppel
    -0.61
     compares
    -0.60
    POSITIVE LOGITS
     confidentiality
    1.32
     privacy
    1.18
     laws
    1.11
     prohibitions
    1.11
     rights
    1.07
     obligations
    1.05
     norms
    1.05
     principles
    1.03
     tenets
    1.02
     neutrality
    1.00
    Activations Density 0.159%

    No Known Activations