© 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. 11434
    Prev
    Next
    INDEX
    Explanations

    changes or shifts in various contexts or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to changes in political, social, or economic conditions

    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
    lees
    -0.72
    netflix
    -0.72
    ogg
    -0.71
    ľ
    -0.71
     Unlimited
    -0.67
    iland
    -0.67
    xxx
    -0.67
    pots
    -0.66
    ãĥĥãĤ¯
    -0.66
    jam
    -0.65
    POSITIVE LOGITS
     attitude
    1.37
     attitudes
    1.25
     mindset
    1.22
     mentality
    1.17
     terminology
    1.16
     tone
    1.14
     methodology
    1.13
     perception
    1.10
     direction
    1.10
     emphasis
    1.10
    Activations Density 0.129%

    No Known Activations