© 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. 8-RES-JB
    11. 17908
    Prev
    Next
    INDEX
    Explanations

    words related to fighting or combat

    oai_token-act-pair · gpt-3.5-turbo

    the word "gladiator" and related variations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TAIN
    -0.81
    cles
    -0.77
    CLASSIFIED
    -0.74
    cules
    -0.72
    hyde
    -0.67
    ÄŁ
    -0.67
     recommend
    -0.63
    ÃįÃį
    -0.63
     approve
    -0.62
    ITAL
    -0.62
    POSITIVE LOGITS
    itz
    1.15
    itched
    1.14
    adiator
    1.13
    ancing
    1.12
    acial
    1.11
    oppy
    1.08
    anz
    1.06
    immer
    1.06
    itching
    1.02
    utton
    1.02
    Activations Density 0.015%

    No Known Activations