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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 10-RES-JB
    6. 19250
    Prev
    Next
    INDEX
    Explanations

    the concept of emptiness or lack of information

    oai_token-act-pair · gpt-3.5-turbo

    references to emptiness or lack of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVERS
    -0.84
    tis
    -0.82
    byn
    -0.80
    xual
    -0.75
    grad
    -0.74
    annis
    -0.72
    amen
    -0.69
     sidx
    -0.68
     horm
    -0.67
    IVER
    -0.65
    POSITIVE LOGITS
    eting
    1.51
     slate
    1.32
    ety
    1.11
     stares
    0.99
    ness
    0.97
     canvas
    0.96
    etry
    0.94
     stare
    0.93
     Slate
    0.88
    ed
    0.85
    Activations Density 0.023%

    No Known Activations