© 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. 12-RES-JB
    11. 3436
    Prev
    Next
    INDEX
    Explanations

    expressions or statements related to customer entitlement and perceptions of success in various industries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    criticisms of customer expectations regarding product accountability and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Kissinger
    -1.01
     Roosevelt
    -0.89
     Rhodes
    -0.88
     Windsor
    -0.87
     Eisenhower
    -0.86
     Glou
    -0.80
     FDR
    -0.80
     Chamberlain
    -0.77
     Oswald
    -0.77
     Newark
    -0.76
    POSITIVE LOGITS
    yout
    1.20
     devs
    1.19
    Developer
    1.13
    ̶
    1.09
    ãĥīãĥ©
    1.05
    shit
    1.04
    advertisement
    1.03
    develop
    1.03
    âĢ
    1.03
    mercial
    1.02
    Activations Density 0.943%

    No Known Activations