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. 0-RES-JB
    6. 19767
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to precision and specificity

    oai_token-act-pair · gpt-3.5-turbo

    references to precision and specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anga
    -0.64
    endum
    -0.64
    stay
    -0.64
    akia
    -0.62
    ende
    -0.62
    bean
    -0.61
    rib
    -0.59
     Communities
    -0.59
    news
    -0.58
     Networks
    -0.58
    POSITIVE LOGITS
     exact
    3.84
     precise
    2.20
     approximate
    1.53
     exactly
    1.35
    same
    1.31
     same
    1.30
     specifics
    1.24
    Exactly
    1.20
     actual
    1.18
     absolute
    1.14
    Activations Density 0.012%

    No Known Activations