© 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. 9-RES-JB
    11. 17696
    Prev
    Next
    INDEX
    Explanations

    names of media outlets and individuals, as well as phrases related to critiquing articles or media content

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to demands or calls for action, particularly in a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mares
    -0.74
     Pwr
    -0.71
     guiIcon
    -0.68
    rentices
    -0.66
    iership
    -0.66
    rastructure
    -0.64
    ropolitan
    -0.61
    ende
    -0.60
     realise
    -0.60
    ÃĥÃĤ
    -0.59
    POSITIVE LOGITS
     "#
    1.49
     "@
    1.22
     "[
    1.05
     "'
    1.04
     "âĢ¦
    1.00
     Yiannopoulos
    0.98
     plagiar
    0.96
     "...
    0.93
     "_
    0.87
     boycott
    0.87
    Activations Density 1.332%

    No Known Activations