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. 8-RES-JB
    6. 19699
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaining ground, dominance, and prominence

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with gaining power or control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inflamm
    -0.67
     countdown
    -0.64
     lockout
    -0.61
     typo
    -0.59
     deliberate
    -0.59
     Declaration
    -0.58
     summary
    -0.55
     abst
    -0.54
    urst
    -0.54
     Sew
    -0.53
    POSITIVE LOGITS
     nationally
    0.99
    hare
    0.93
     internationally
    0.93
     abroad
    0.92
     overseas
    0.91
     amongst
    0.88
     Flavoring
    0.87
     amidst
    0.86
     domestically
    0.84
     globally
    0.82
    Activations Density 0.325%

    No Known Activations