© 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. 11287
    Prev
    Next
    INDEX
    Explanations

    sentences expressing strong negative opinions or reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of outrage and condemnation

    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
    achus
    -0.73
     eas
    -0.70
    vati
    -0.65
     optim
    -0.65
     arrangement
    -0.61
     incorporation
    -0.61
     auxiliary
    -0.61
     recovers
    -0.60
    soDeliveryDate
    -0.60
     Ascension
    -0.59
    POSITIVE LOGITS
     despicable
    1.51
     disgrace
    1.51
     appalling
    1.44
     disgusting
    1.41
     unacceptable
    1.37
     abhor
    1.30
     intolerable
    1.28
     shameful
    1.24
     depl
    1.24
     vile
    1.23
    Activations Density 0.642%

    No Known Activations