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. 3-RES-JB
    6. 22352
    Prev
    Next
    INDEX
    Explanations

    words related to refurbishment or alteration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "refactoring"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Merit
    -0.88
    人
    -0.72
    Cru
    -0.67
    sky
    -0.65
    è£ħ
    -0.64
    ahime
    -0.63
    Jr
    -0.63
     è£ıè
    -0.62
    ppa
    -0.61
    æĺ
    -0.61
    POSITIVE LOGITS
    ascript
    0.80
    itory
    0.77
    ndum
    0.74
    issance
    0.70
    ition
    0.68
    ysis
    0.67
    essors
    0.67
    ractive
    0.65
    ance
    0.65
    unda
    0.64
    Activations Density 0.039%

    No Known Activations