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. 8895
    Prev
    Next
    INDEX
    Explanations

    verbs related to accomplishment or success

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions, outcomes, and conditions tied to 'wish,' 'vanish,' 'accomplish,' and similar verb forms

    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
     calculated
    -0.60
     measured
    -0.58
     squared
    -0.58
     moder
    -0.58
     Math
    -0.57
     panel
    -0.57
     RIS
    -0.57
     robust
    -0.57
     live
    -0.57
     Bruce
    -0.56
    POSITIVE LOGITS
    ishes
    4.64
    ishing
    2.83
    ished
    2.61
    ishers
    2.38
    ISH
    2.21
    ish
    2.20
    ishment
    1.96
    isher
    1.95
    ishly
    1.76
    ishable
    1.70
    Activations Density 0.004%

    No Known Activations