© 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. 2-RES-JB
    11. 9156
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to military battalions

    oai_token-act-pair · gpt-3.5-turbo

    references to military organizations, particularly those related to battalions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.81
    çīĪ
    -0.70
    çĶŁ
    -0.69
    596
    -0.67
     Âł Âł Âł Âł
    -0.64
     fixation
    -0.64
     wee
    -0.64
    ãĥĪ
    -0.63
    794
    -0.63
    594
    -0.63
    POSITIVE LOGITS
    alions
    1.37
    leground
    1.31
     Batt
    1.08
    anooga
    1.00
    auld
    0.98
    raph
    0.96
    eenth
    0.94
    anche
    0.93
    lest
    0.92
    lett
    0.91
    Activations Density 0.003%

    No Known Activations