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. 10-RES-JB
    6. 105
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "least" or things of minimal preference

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the concept of "least" or "least liked."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.82
    ses
    -0.81
    çīĪ
    -0.70
    clerosis
    -0.67
    andise
    -0.67
     Reborn
    -0.65
    stru
    -0.64
    WithNo
    -0.64
    pez
    -0.64
    zie
    -0.63
    POSITIVE LOGITS
     intrusive
    0.94
     amount
    0.93
     objectionable
    0.88
     bit
    0.86
     restrictive
    0.81
     detectable
    0.81
     imaginable
    0.80
    ening
    0.77
     expensive
    0.75
     risky
    0.74
    Activations Density 0.019%

    No Known Activations