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

    Neuronpedia

    Jacobian LensNEW
    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. 2358
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of acts conducted by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    various forms of "act" related to concepts of aggression, violence, and morality

    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
    kees
    -0.79
     sshd
    -0.75
    ials
    -0.75
    devices
    -0.74
     Lines
    -0.74
     Flavoring
    -0.73
     strands
    -0.69
     facets
    -0.68
    levels
    -0.67
     Transcript
    -0.67
    POSITIVE LOGITS
     kindness
    1.20
     vandalism
    1.14
     defiance
    1.09
     sabotage
    1.09
     heroism
    1.06
     aggression
    1.04
     desperation
    1.02
     generosity
    1.00
     bravery
    0.97
     solidarity
    0.94
    Activations Density 0.060%

    No Known Activations