© 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. 6-RES-JB
    11. 12324
    Prev
    Next
    INDEX
    Explanations

    first-person singular verbs ending in 'ed'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "I'd."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tension
    -0.63
     rigging
    -0.62
    zai
    -0.61
     Remem
    -0.60
     Tayyip
    -0.60
     momentum
    -0.60
     tensions
    -0.57
     Lambert
    -0.57
     constitu
    -0.57
     Sut
    -0.57
    POSITIVE LOGITS
    ividual
    1.39
    iversity
    1.10
    iamond
    1.02
    rew
    1.01
    ynamic
    0.94
    ynam
    0.93
    roid
    0.93
    istant
    0.92
    iverse
    0.92
    iscover
    0.90
    Activations Density 0.024%

    No Known Activations