© 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. 15779
    Prev
    Next
    INDEX
    Explanations

    phrases related to political coalitions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "coalition" along with punctuation that marks the beginning of a document

    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
    lycer
    -0.83
    icago
    -0.69
    agate
    -0.64
     Converted
    -0.64
    ials
    -0.64
     Hof
    -0.64
    rors
    -0.64
    hibited
    -0.63
    orgetown
    -0.63
    perature
    -0.63
    POSITIVE LOGITS
    naire
    1.01
     partners
    0.95
     footing
    0.89
     Provision
    0.87
     partner
    0.86
     member
    0.82
    leader
    0.79
     alliances
    0.79
     formed
    0.79
     mates
    0.79
    Activations Density 0.047%

    No Known Activations