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. 7-RES-JB
    6. 16393
    Prev
    Next
    INDEX
    Explanations

    words related to emptiness or lack of content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blank" and related concepts of emptiness or absence

    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
    IVERS
    -0.81
    IVER
    -0.81
    annis
    -0.76
    HI
    -0.74
    ~~~~~~~~~~~~~~~~
    -0.71
    appropriate
    -0.69
    WAYS
    -0.68
    CVE
    -0.68
    tis
    -0.67
    byn
    -0.66
    POSITIVE LOGITS
    eting
    1.24
     slate
    1.12
     stares
    1.02
    ety
    1.00
    cies
    0.89
    ness
    0.86
    etry
    0.83
     blank
    0.79
    erness
    0.79
     stare
    0.78
    Activations Density 0.026%

    No Known Activations