© 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. 3-RES-JB
    11. 15122
    Prev
    Next
    INDEX
    Explanations

    restrictions imposed on various subjects

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various restrictions imposed by authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rious
    -0.75
    psc
    -0.71
    story
    -0.70
    earth
    -0.67
    amina
    -0.66
    Sea
    -0.65
     Generations
    -0.64
     Dirt
    -0.62
    rouse
    -0.62
    ashington
    -0.62
    POSITIVE LOGITS
     restrictions
    1.17
     restricting
    1.12
     imposed
    1.12
     prohibited
    1.02
     restricts
    0.97
     inhib
    0.93
     restriction
    0.93
     prohibiting
    0.91
     restricted
    0.90
     restrictive
    0.90
    Activations Density 0.013%

    No Known Activations