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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 3-RES-JB
    6. 11717
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings and emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Secondly
    -0.71
    adish
    -0.71
     Shutterstock
    -0.70
    licensed
    -0.70
    olesc
    -0.68
     Chim
    -0.68
     Camer
    -0.65
    atile
    -0.63
     Display
    -0.62
     Leap
    -0.62
    POSITIVE LOGITS
     comfortable
    0.92
     vibrations
    0.87
     compelled
    0.81
    ãĤ¶
    0.81
     sensations
    0.81
    OWS
    0.80
     uneasy
    0.78
     uncomfortable
    0.77
     felt
    0.74
     nostalgic
    0.73
    Activations Density 0.040%

    No Known Activations