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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 312
    Prev
    Next
    INDEX
    Explanations

    references to emotions and feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating various feelings or perceptions of "sense."

    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
    sites
    -0.82
    annis
    -0.81
    onial
    -0.76
    theless
    -0.74
    morrow
    -0.67
    ceed
    -0.66
    solete
    -0.66
    mercial
    -0.64
     downed
    -0.61
    dule
    -0.60
    POSITIVE LOGITS
    ively
    0.90
     sense
    0.79
     urgency
    0.76
    omatic
    0.74
    Msg
    0.71
     compulsion
    0.71
    eely
    0.71
    IFT
    0.70
    ibly
    0.68
    UAL
    0.68
    Activations Density 0.018%

    No Known Activations