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. 6-RES-JB
    6. 4493
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'refuge'

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "refuge" and related concepts

    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
     Mub
    -0.65
    ahime
    -0.64
     Closed
    -0.63
     stakes
    -0.63
     disadvant
    -0.63
    Ͻ
    -0.60
    grey
    -0.59
    ashtra
    -0.59
     advant
    -0.58
     disadvantage
    -0.57
    POSITIVE LOGITS
    issance
    0.86
    ndum
    0.84
    itory
    0.83
    ruary
    0.77
    vernment
    0.71
    itte
    0.70
    ibly
    0.69
    cled
    0.69
     Latvia
    0.68
    rocal
    0.68
    Activations Density 0.110%

    No Known Activations