© 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. 7-RES-JB
    11. 21279
    Prev
    Next
    INDEX
    Explanations

    information related to various aspects of society and public affairs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal and governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yorkers
    -0.80
    orsi
    -0.79
    paio
    -0.75
    HCR
    -0.67
    oldemort
    -0.67
    atism
    -0.63
    enegger
    -0.63
    umbledore
    -0.62
    olicited
    -0.62
    loads
    -0.62
    POSITIVE LOGITS
     vicinity
    1.23
     realm
    1.17
     arena
    1.12
     context
    1.03
     universe
    1.00
     aisle
    1.00
     area
    0.98
     guise
    0.95
    osphere
    0.93
     confines
    0.91
    Activations Density 0.446%

    No Known Activations