© 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. 23646
    Prev
    Next
    INDEX
    Explanations

    words related to cannons or cannon fire

    oai_token-act-pair · gpt-3.5-turbo

    references to cannons or artillery-related terminology

    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
    ©¶æ
    -0.89
    lihood
    -0.88
    Else
    -0.84
    Sea
    -0.71
    Sense
    -0.71
    ĪĴ
    -0.68
    æĸ¹
    -0.68
    mone
    -0.67
     Dietary
    -0.67
    Office
    -0.65
    POSITIVE LOGITS
    balls
    1.15
     cannon
    1.13
    lance
    1.13
     cannons
    1.05
    ball
    1.04
     fodder
    0.99
     Cannon
    0.93
     salute
    0.87
    illon
    0.85
     bombard
    0.85
    Activations Density 0.015%

    No Known Activations