© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 20477
    Prev
    Next
    INDEX
    Explanations

    phrases related to different professions and roles

    oai_token-act-pair · gpt-3.5-turbo

    identifiers related to personal roles or identities

    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
     \'
    -0.74
    ombies
    -0.61
    videos
    -0.61
    rists
    -0.60
    Stars
    -0.60
    >]
    -0.59
    odo
    -0.57
    COMPLE
    -0.57
    åħī
    -0.57
    andals
    -0.57
    POSITIVE LOGITS
     myself
    1.29
     yourself
    0.91
     oneself
    0.89
     ourselves
    0.89
     accustomed
    0.84
     educator
    0.82
     grows
    0.78
     I
    0.77
     we
    0.77
     yourselves
    0.75
    Activations Density 0.114%

    No Known Activations