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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18659
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies, regulations, and standards

    oai_token-act-pair · gpt-3.5-turbo

    references to standards and regulatory compliance

    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
    asonic
    -0.78
    ventus
    -0.77
     whilst
    -0.76
    ogyn
    -0.74
    ingly
    -0.72
    utenant
    -0.72
    lest
    -0.72
    ESPN
    -0.72
    wich
    -0.71
    Team
    -0.70
    POSITIVE LOGITS
     remainder
    1.13
     rollout
    1.08
     project
    1.01
     nascent
    0.99
     process
    0.98
     arrangement
    0.98
     burgeoning
    0.95
     proposal
    0.94
     newfound
    0.93
     controversial
    0.93
    Activations Density 0.401%

    No Known Activations