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. 8982
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs indicating a permanent or long-lasting state

    oai_token-act-pair · gpt-3.5-turbo

    terms related to permanence or lasting effects

    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
     ay
    -0.68
     Committees
    -0.61
     math
    -0.60
    rics
    -0.59
     Struggle
    -0.58
    rick
    -0.58
     gust
    -0.58
    ait
    -0.57
    ieu
    -0.57
    zen
    -0.57
    POSITIVE LOGITS
     permanently
    3.45
     temporarily
    2.12
     indefinitely
    1.88
     forever
    1.66
     permanent
    1.66
     prematurely
    1.46
     securely
    1.38
     perpetually
    1.31
     completely
    1.24
     momentarily
    1.18
    Activations Density 0.014%

    No Known Activations