© 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. 9977
    Prev
    Next
    INDEX
    Explanations

    phrases related to military tactics and strategies

    oai_token-act-pair · gpt-3.5-turbo

    references to strategies for overcoming challenges in competitive scenarios

    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
     Coff
    -0.72
     limbo
    -0.70
     Journals
    -0.69
     autobi
    -0.68
    abilia
    -0.66
     holiday
    -0.65
    translation
    -0.65
    holiday
    -0.64
     Loft
    -0.64
     tourism
    -0.63
    POSITIVE LOGITS
     defeat
    1.40
     Defeat
    1.37
     defeated
    1.34
     foe
    1.33
     defeating
    1.31
     vanquished
    1.31
     adversary
    1.29
     opponent
    1.26
     outnumbered
    1.26
     fight
    1.26
    Activations Density 0.661%

    No Known Activations