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. 8311
    Prev
    Next
    INDEX
    Explanations

    verbs related to avoiding something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to evading difficult or unwanted situations

    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
    raq
    -0.89
    uid
    -0.83
    lease
    -0.80
    tek
    -0.76
    STAT
    -0.75
    soon
    -0.73
    Roy
    -0.71
    old
    -0.70
    nai
    -0.69
    hered
    -0.69
    POSITIVE LOGITS
     pitfalls
    1.37
     wasting
    1.13
     detection
    1.12
     harming
    1.08
     mentioning
    1.06
     collisions
    1.06
     distractions
    1.05
     paying
    1.05
     confrontation
    1.05
     unnecessary
    1.04
    Activations Density 0.074%

    No Known Activations