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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 18373
    Prev
    Next
    INDEX
    Explanations

    instances of statements or situations with a strong emotional impact

    oai_token-act-pair · gpt-3.5-turbo

    prominent adjectives that convey significance or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     safely
    -0.65
    iphate
    -0.64
     Rohingya
    -0.63
    ntil
    -0.62
    gettable
    -0.62
    iasco
    -0.61
     Chargers
    -0.61
    icipated
    -0.61
     persecuted
    -0.59
     stoked
    -0.59
    POSITIVE LOGITS
     proportions
    0.75
     mode
    0.72
    oru
    0.69
    history
    0.68
     origin
    0.68
    mia
    0.66
    thia
    0.65
     circumstances
    0.65
     ausp
    0.63
    credit
    0.62
    Activations Density 0.463%

    No Known Activations