© 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. 16035
    Prev
    Next
    INDEX
    Explanations

    phrases related to social or cultural trends

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing actions or tendencies in people's behaviors and beliefs

    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
    ãĥ´ãĤ¡
    -0.78
    maximum
    -0.69
    Alright
    -0.68
     Kills
    -0.63
    player
    -0.63
     lasts
    -0.62
     predecessor
    -0.62
     Contains
    -0.61
     Resurrection
    -0.61
     Directions
    -0.61
    POSITIVE LOGITS
     complain
    1.24
     perceive
    1.24
     shun
    1.14
     willingly
    1.13
     voluntarily
    1.10
     instinctively
    1.10
     migrate
    1.09
     flock
    1.08
     prefer
    1.06
     resent
    1.06
    Activations Density 0.515%

    No Known Activations