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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22462
    Prev
    Next
    INDEX
    Explanations

    numbers or measurements, such as percentages and year references

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social structures and 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
    Sources
    -0.84
    units
    -0.73
     Reports
    -0.71
     Plans
    -0.71
    models
    -0.71
     Parties
    -0.70
     PACs
    -0.70
     Administ
    -0.69
    bows
    -0.69
     Sections
    -0.69
    POSITIVE LOGITS
     wherein
    0.84
    mma
    0.83
     against
    0.82
    ness
    0.80
    undrum
    0.79
    ortment
    0.79
    hander
    0.79
    swer
    0.76
    ence
    0.76
    iment
    0.76
    Activations Density 0.507%

    No Known Activations