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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13222
    Prev
    Next
    INDEX
    Explanations

    phrases related to software updates and bug fixes

    oai_token-act-pair · gpt-3.5-turbo

    references to bugs and improvements in software updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.82
    bia
    -0.75
     Americ
    -0.73
    educ
    -0.72
    Allen
    -0.70
    aden
    -0.67
    uron
    -0.67
    CTV
    -0.67
    PRES
    -0.66
    UCT
    -0.65
    POSITIVE LOGITS
     tweaks
    0.96
     ner
    0.94
    fixes
    0.92
     workaround
    0.84
     optimizations
    0.84
    webkit
    0.84
     SDK
    0.82
     shader
    0.80
     introduced
    0.79
     tweak
    0.79
    Activations Density 0.114%

    No Known Activations