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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 21865
    Prev
    Next
    INDEX
    Explanations

    the word "give" followed by an object pronoun

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experience and requests

    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
    eness
    -0.77
    trak
    -0.67
    amiya
    -0.64
    _.
    -0.63
     arous
    -0.61
     Anxiety
    -0.60
    ami
    -0.60
    issy
    -0.59
     reperc
    -0.57
    amazon
    -0.56
    POSITIVE LOGITS
    ãģ¦
    0.78
    çīĪ
    0.72
     scraps
    0.71
    ãĤ¡
    0.71
    rov
    0.71
     ample
    0.68
    å§
    0.68
     hope
    0.65
    ãĥª
    0.65
     pause
    0.65
    Activations Density 0.087%

    No Known Activations