© 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. 8-RES-JB
    11. 10961
    Prev
    Next
    INDEX
    Explanations

    words related to actions or events involving significant individuals or figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "he" and related actions

    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
     downside
    -0.80
    quickShipAvailable
    -0.71
     srfAttach
    -0.68
    ector
    -0.64
    Els
    -0.64
    soType
    -0.62
    growth
    -0.61
    channelAvailability
    -0.60
    IOR
    -0.59
    Others
    -0.59
    POSITIVE LOGITS
     accidentally
    1.01
     knowingly
    0.95
     intentionally
    0.91
     systematically
    0.90
     forcibly
    0.89
     unilaterally
    0.86
     inadvertently
    0.85
     purposely
    0.84
     befriend
    0.83
     selectively
    0.83
    Activations Density 0.842%

    No Known Activations