© 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. 7093
    Prev
    Next
    INDEX
    Explanations

    phrases related to slowing down or calming down

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to slowing down or calming down

    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
    è¦ļéĨĴ
    -0.86
    çīĪ
    -0.81
    sonian
    -0.75
    nard
    -0.71
     Cosponsors
    -0.69
    lez
    -0.68
    eport
    -0.68
     congr
    -0.67
    iaries
    -0.67
    APH
    -0.67
    POSITIVE LOGITS
    motion
    0.95
    notice
    0.76
    Motion
    0.71
    downs
    0.71
     breathing
    0.64
    pps
    0.61
    tics
    0.60
     JavaScript
    0.60
    oxide
    0.59
     inertia
    0.59
    Activations Density 0.214%

    No Known Activations