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. 2-RES-JB
    6. 9580
    Prev
    Next
    INDEX
    Explanations

    phrases related to sustaining and describing various entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to descriptions and the concept of sustainability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heaven
    -0.70
    Reviewer
    -0.69
     Wonderland
    -0.66
     PBS
    -0.65
     Bir
    -0.63
     Mitt
    -0.63
     Dragonbound
    -0.62
    ħĭ
    -0.59
    EMS
    -0.59
     nuts
    -0.58
    POSITIVE LOGITS
    ript
    1.46
    ribing
    1.24
    ribed
    1.15
    desc
    1.14
    endants
    1.14
    ribe
    1.12
    ribes
    1.09
    endant
    1.04
    ended
    0.98
    ributes
    0.92
    Activations Density 0.006%

    No Known Activations