© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 5356
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions and events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clus
    -0.81
    icent
    -0.80
     eas
    -0.80
     superiority
    -0.79
     niche
    -0.79
    usal
    -0.79
    ecided
    -0.78
     favourable
    -0.76
    eker
    -0.76
     upbeat
    -0.75
    POSITIVE LOGITS
     Worse
    1.87
     Fortunately
    1.53
     Luckily
    1.49
     Thankfully
    1.45
     Symptoms
    1.36
     Unable
    1.25
     Eventually
    1.23
     Victims
    1.22
     Hundreds
    1.22
     Literally
    1.19
    Activations Density 0.543%

    No Known Activations