Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2910
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to a particular entity or topic ("Ey")

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept or entity represented by "Ey."

    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
    士
    -0.74
    د
    -0.71
     containment
    -0.71
    å§«
    -0.69
     congr
    -0.66
    Ø©
    -0.63
     mate
    -0.62
    UTION
    -0.60
     saline
    -0.59
     breeding
    -0.59
    POSITIVE LOGITS
    ewitness
    1.23
    Ey
    1.08
    gments
    1.05
    eworks
    1.00
    ringe
    0.99
    seys
    0.95
    etooth
    0.89
    esh
    0.89
    eless
    0.88
    eg
    0.88
    Activations Density 0.036%

    No Known Activations