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. 11-RES-JB
    6. 10663
    Prev
    Next
    INDEX
    Explanations

    words related to necessity and importance

    oai_token-act-pair · gpt-3.5-turbo

    conditional and duality statements regarding necessity and proportion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    knife
    -0.79
    mares
    -0.78
    afia
    -0.74
     Cosponsors
    -0.73
    EStream
    -0.72
    IPS
    -0.72
    online
    -0.71
    moil
    -0.70
    lag
    -0.70
     Split
    -0.70
    POSITIVE LOGITS
     desirable
    1.46
     unavoidable
    1.43
     achievable
    1.38
     inevitable
    1.33
     necessary
    1.33
     advisable
    1.31
     worthwhile
    1.27
     acceptable
    1.25
     beneficial
    1.22
     permissible
    1.16
    Activations Density 0.234%

    No Known Activations