© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 7330
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'of course'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey certainty or a common acknowledgment, often introducing statements that discuss shared beliefs or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewed
    -0.82
    CI
    -0.73
    Dialog
    -0.69
    pan
    -0.65
    HUD
    -0.63
    panel
    -0.63
    Released
    -0.61
    Prep
    -0.61
    ively
    -0.60
    idden
    -0.59
    POSITIVE LOGITS
     caveat
    0.72
     caveats
    0.70
     assumes
    0.70
     begs
    0.70
    ;;;;;;;;
    0.67
    iov
    0.66
    chio
    0.65
    ueller
    0.64
     Kinnikuman
    0.64
     horr
    0.62
    Activations Density 0.152%

    No Known Activations