© 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. 8213
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to personal characteristics or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "being."

    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
    PsyNetMessage
    -0.76
    inav
    -0.72
     fray
    -0.66
    orrow
    -0.62
     Lag
    -0.62
     Times
    -0.61
     Globe
    -0.61
     Landing
    -0.60
    NetMessage
    -0.60
     margin
    -0.58
    POSITIVE LOGITS
     able
    1.47
     unable
    1.08
     aware
    1.04
     overwhelmed
    0.90
     immersed
    0.89
     deprived
    0.89
     proactive
    0.89
     mindful
    0.87
     bitten
    0.86
     eaten
    0.86
    Activations Density 0.079%

    No Known Activations