© 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. 0-RES-JB
    11. 614
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'wedding' or 'wedge'

    oai_token-act-pair · gpt-3.5-turbo

    references to marriages and wedlock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Astral
    -0.76
    ISA
    -0.76
     Rail
    -0.75
    ère
    -0.70
    INA
    -0.67
    oa
    -0.67
    mins
    -0.67
     LEVEL
    -0.66
     Richie
    -0.66
     DAC
    -0.66
    POSITIVE LOGITS
     wed
    3.80
     wedge
    2.88
     Wed
    2.22
    wed
    2.18
    Wed
    1.84
     dow
    1.17
     Thu
    1.09
    obar
    1.06
    Thu
    1.00
     Tue
    1.00
    Activations Density 0.029%

    No Known Activations