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. 3-RES-JB
    6. 21953
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of tolerance, including both positive and negative contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of tolerance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.83
    prints
    -0.76
    inet
    -0.69
    cester
    -0.69
    grave
    -0.69
    vet
    -0.68
    joining
    -0.68
    join
    -0.68
    gin
    -0.66
    bleacher
    -0.66
    POSITIVE LOGITS
     tolerance
    1.21
     tolerant
    1.11
    olerance
    1.06
     intolerance
    1.01
     toler
    0.97
     intoler
    0.95
     tolerate
    0.82
     sensitivity
    0.80
     tolerated
    0.78
    terness
    0.75
    Activations Density 0.009%

    No Known Activations