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. 2-RES-JB
    6. 2515
    Prev
    Next
    INDEX
    Explanations

    words related to caring or concern for others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of care or concern for others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prohibition
    -0.81
    è¦ļéĨĴ
    -0.73
    ãĥ³ãĤ¸
    -0.71
     transcript
    -0.65
     resume
    -0.63
     resumes
    -0.63
     perjury
    -0.62
     confirmation
    -0.62
     Yugoslavia
    -0.61
     projection
    -0.59
    POSITIVE LOGITS
     cared
    1.16
    lessly
    1.02
    taker
    0.93
    amily
    0.78
    giving
    0.77
    rals
    0.76
    fully
    0.73
    der
    0.73
    lest
    0.73
    lington
    0.72
    Activations Density 0.012%

    No Known Activations