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. 5-RES-JB
    6. 2700
    Prev
    Next
    INDEX
    Explanations

    strong emotional reactions such as being saddened, disappointed, appalled, horrified, or shocked

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong negative emotions, particularly sadness, disappointment, and horror

    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
     livest
    -0.69
     cheat
    -0.68
    Ranked
    -0.67
    enture
    -0.67
    soDeliveryDate
    -0.66
    pmwiki
    -0.66
     dated
    -0.65
    checks
    -0.63
     sneak
    -0.63
    sites
    -0.62
    POSITIVE LOGITS
     aback
    0.85
    vier
    0.74
     saddened
    0.73
    dy
    0.72
    urous
    0.69
     citiz
    0.66
     enough
    0.66
    ORK
    0.65
     seeing
    0.64
    ãĤ¦ãĤ¹
    0.64
    Activations Density 0.086%

    No Known Activations