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. 11-RES-JB
    6. 10799
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions or attitudes towards a person or situation

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments and expressions of disappointment or disgust

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.72
     cycle
    -0.71
     Transition
    -0.69
     hike
    -0.69
     sealing
    -0.68
     hiking
    -0.68
     rotation
    -0.68
     density
    -0.67
     playback
    -0.66
     flow
    -0.65
    POSITIVE LOGITS
    ceptive
    1.26
    ignant
    1.24
    atisf
    1.19
    interested
    1.16
    otent
    1.15
    respect
    1.12
    urious
    1.12
    isive
    1.10
    assion
    1.08
    righteous
    1.07
    Activations Density 0.132%

    No Known Activations