© 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. 5999
    Prev
    Next
    INDEX
    Explanations

    verbs related to being impacted or affected negatively

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hit" in various contexts related to impact or suffering

    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
     vantage
    -0.66
    resso
    -0.57
     Conversation
    -0.55
     acceptance
    -0.54
     perspectives
    -0.54
     viewpoint
    -0.54
     Representatives
    -0.52
     perspective
    -0.51
     Integ
    -0.51
    estate
    -0.51
    POSITIVE LOGITS
     by
    1.02
     hardest
    1.00
    ribly
    0.92
     hard
    0.91
     badly
    0.91
    ãĤ°
    0.88
     unfairly
    0.83
     merciless
    0.83
     harder
    0.82
    cule
    0.81
    Activations Density 0.112%

    No Known Activations