Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 515
    Prev
    Next
    INDEX
    Explanations

    keywords related to agreements or compromises, often involving concessions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "concession."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nan
    -0.68
    opes
    -0.62
    psc
    -0.62
    chem
    -0.61
    nin
    -0.61
     Lyme
    -0.60
    ²¾
    -0.60
    ross
    -0.60
    mind
    -0.59
    energy
    -0.59
    POSITIVE LOGITS
     concessions
    1.19
     concession
    1.09
    ļéĨĴ
    0.87
    aires
    0.84
     bargain
    0.78
    aire
    0.78
    cession
    0.76
    ensical
    0.75
     amnesty
    0.75
    serv
    0.73
    Activations Density 0.027%

    No Known Activations