© 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. 9-RES-JB
    11. 17410
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and issues related to current events

    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
    *.
    -0.71
    irlf
    -0.68
    .).
    -0.68
    `.
    -0.67
    $.
    -0.65
    %.
    -0.65
    +.
    -0.64
    Joined
    -0.62
    ebus
    -0.61
    !".
    -0.60
    POSITIVE LOGITS
     varies
    1.32
     depends
    1.21
     coincides
    1.15
     coincided
    1.10
     involves
    1.10
     differs
    1.02
     indicates
    1.02
     depended
    1.00
     extends
    1.00
     underscores
    0.99
    Activations Density 0.874%

    No Known Activations