© 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. 2-RES-JB
    11. 20846
    Prev
    Next
    INDEX
    Explanations

    references to physical barriers, specifically fencing, in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fencing in various contexts

    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
    ODUCT
    -0.74
    PET
    -0.71
    ove
    -0.68
    OSP
    -0.67
     Advertisement
    -0.67
    Mars
    -0.66
    ular
    -0.66
     Khe
    -0.64
    OS
    -0.63
    Mos
    -0.62
    POSITIVE LOGITS
     fencing
    1.34
     swords
    0.97
     mathemat
    0.95
     duel
    0.86
    arnaev
    0.83
     apprentices
    0.80
    manship
    0.78
    ateurs
    0.77
    ratulations
    0.75
     sword
    0.74
    Activations Density 0.030%

    No Known Activations