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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7081
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases with negative sentiments or expressions of disappointment

    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
     Dickinson
    -0.74
     appropri
    -0.69
     leaps
    -0.66
     outlet
    -0.65
    ="/
    -0.62
     bounds
    -0.61
     refugee
    -0.60
     decon
    -0.60
     fleeing
    -0.59
     fortunes
    -0.59
    POSITIVE LOGITS
    =-=-=-=-=-=-=-=-
    1.33
    _-
    1.24
    =-=-=-=-
    1.22
    webkit
    1.20
     Advertisement
    1.08
    sama
    1.02
    eric
    0.95
    *=-
    0.93
    /-
    0.86
     Stuff
    0.80
    Activations Density 0.020%

    No Known Activations