© 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. 11-RES-JB
    11. 5034
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to authority and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wet
    -0.79
    amaz
    -0.76
     Gravity
    -0.76
    fixes
    -0.73
    ðŁĺ
    -0.73
    ooked
    -0.71
    Dro
    -0.70
     Crazy
    -0.70
    Speed
    -0.69
     Turns
    -0.69
    POSITIVE LOGITS
     participate
    1.39
     undertake
    1.27
     engage
    1.24
     profess
    1.23
     endorse
    1.22
     collaborate
    1.21
     wield
    1.21
     embody
    1.20
     denounce
    1.19
     partake
    1.19
    Activations Density 0.350%

    No Known Activations