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. 1265
    Prev
    Next
    INDEX
    Explanations

    negative words related to unhappiness and poor conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with negative emotional states or poor conditions

    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
    •layer 5 - sadness

    No Comments

    Negative Logits
    omen
    -0.88
    ioch
    -0.86
    ortium
    -0.84
    encers
    -0.84
    icipated
    -0.80
    tnc
    -0.79
    encer
    -0.78
    illance
    -0.77
    leans
    -0.75
    natureconservancy
    -0.74
    POSITIVE LOGITS
     miserable
    0.86
     nightmare
    0.69
     Goods
    0.68
     excuse
    0.68
     donkey
    0.68
     excuses
    0.67
     dismal
    0.66
     bastard
    0.66
     disappoint
    0.65
    abama
    0.65
    Activations Density 0.041%

    No Known Activations