© 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. 8-RES-JB
    11. 20191
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements or decisions

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding official actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chap
    -0.77
    izons
    -0.69
     Stores
    -0.68
     exits
    -0.66
     Hath
    -0.65
     inhabit
    -0.63
    arling
    -0.62
     Horizons
    -0.61
    azines
    -0.61
     pores
    -0.61
    POSITIVE LOGITS
     unacceptable
    1.04
     warranted
    1.00
     merely
    0.99
     akin
    0.96
     unfair
    0.95
     purely
    0.94
     necessary
    0.92
     legitimate
    0.91
     counterproductive
    0.90
     unsustainable
    0.90
    Activations Density 0.312%

    No Known Activations