© 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. 4-RES-JB
    11. 24139
    Prev
    Next
    INDEX
    Explanations

    phrases related to violations of rules or laws

    oai_token-act-pair · gpt-3.5-turbo

    references to legal violations and rights

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

    No Comments

    Negative Logits
    acs
    -0.88
    onna
    -0.80
    vale
    -0.76
    borgh
    -0.76
    uilding
    -0.74
    ussen
    -0.73
    isSpecialOrderable
    -0.72
     dwind
    -0.71
    nis
    -0.71
    ington
    -0.70
    POSITIVE LOGITS
    Ö¼
    0.90
    ł
    0.75
     contractual
    0.75
    Third
    0.75
     norms
    0.73
     jurisdiction
    0.73
     confidentiality
    0.72
    ĺħ
    0.72
     principle
    0.71
     precedent
    0.71
    Activations Density 0.124%

    No Known Activations