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. 6-RES-JB
    6. 19383
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions or sentiments like boredom, resentment, and distrust

    oai_token-act-pair · gpt-3.5-turbo

    words associated with boredom or lack of engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥİ
    -0.81
    esville
    -0.80
    utable
    -0.77
    utes
    -0.70
    zilla
    -0.66
    ortium
    -0.65
    nect
    -0.65
    asel
    -0.65
    esar
    -0.65
    uting
    -0.63
    POSITIVE LOGITS
    MpServer
    0.87
    skirts
    0.80
    tsky
    0.74
    igger
    0.73
    dit
    0.71
    phia
    0.69
    hole
    0.69
    APH
    0.67
    oxin
    0.64
    rums
    0.64
    Activations Density 0.051%

    No Known Activations