© 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 EvalsExportsinterp-engineNEWAPI 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. 3372
    Prev
    Next
    INDEX
    Explanations

    words related to pushing or urging action or change

    oai_token-act-pair · gpt-3.5-turbo

    references to economic and social pressures impacting individuals and groups

    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
    ITNESS
    -0.70
    itutes
    -0.57
    zek
    -0.56
     Chand
    -0.54
     Tribune
    -0.54
     Sins
    -0.53
    claimed
    -0.53
     Eid
    -0.53
     Fitzgerald
    -0.53
     Pact
    -0.53
    POSITIVE LOGITS
     forward
    1.26
     forwards
    1.25
     farther
    1.24
     closer
    1.22
     deeper
    1.10
     further
    1.08
     awa
    1.07
     aside
    1.05
     away
    1.04
     overboard
    1.04
    Activations Density 0.175%

    No Known Activations