© 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. 3185
    Prev
    Next
    INDEX
    Explanations

    sentences expressing an opinion about what actions should be taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases calling for moral or legal accountability

    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
    ullivan
    -0.76
     Wid
    -0.67
     Cros
    -0.65
    lip
    -0.63
    Others
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
    anth
    -0.59
    ous
    -0.59
    NetMessage
    -0.59
    anos
    -0.59
    POSITIVE LOGITS
     avoided
    1.25
     ashamed
    1.19
     applauded
    1.14
     judged
    1.10
     treated
    1.08
     regarded
    1.08
     able
    1.07
     congratulated
    1.03
     viewed
    1.03
     considered
    1.00
    Activations Density 0.098%

    No Known Activations