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. 17504
    Prev
    Next
    INDEX
    Explanations

    references to sports and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various sports and related organizations

    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
     routine
    -0.77
     offence
    -0.74
    onies
    -0.72
    earance
    -0.68
     offense
    -0.68
     stockpile
    -0.67
     brunt
    -0.67
     foreground
    -0.66
     shotgun
    -0.66
     heel
    -0.66
    POSITIVE LOGITS
     Analytics
    1.03
     Matters
    1.00
    Nation
    0.99
    Fix
    0.98
     Digest
    0.98
    Hub
    0.96
    Street
    0.95
    Week
    0.95
     Solutions
    0.94
     Magazine
    0.92
    Activations Density 0.368%

    No Known Activations