© 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 EvalsExportsAPI 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. 9-RES-JB
    11. 14718
    Prev
    Next
    INDEX
    Explanations

    phrases related to inclusion and collaboration, especially when it involves specific countries or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating inclusion or exclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.87
    bis
    -0.84
    ramid
    -0.79
    ciation
    -0.73
    format
    -0.68
    Feature
    -0.67
    ulations
    -0.66
    VERTISEMENT
    -0.66
    ntax
    -0.65
    Scale
    -0.64
    POSITIVE LOGITS
     myself
    1.27
     spouses
    1.13
     yourselves
    1.10
     strangers
    1.09
     oneself
    1.06
     herself
    1.06
     businessmen
    1.05
     Yourself
    1.04
     ourselves
    1.02
     representatives
    1.02
    Activations Density 0.354%

    No Known Activations