© 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. 7417
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions or actions

    oai_token-act-pair · gpt-3.5-turbo

    empty or placeholder text tokens

    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
    Interstitial
    -0.40
     Practices
    -0.38
     deed
    -0.38
    ryu
    -0.37
     Arts
    -0.36
     Norn
    -0.36
    Common
    -0.36
     equivalents
    -0.36
    yne
    -0.36
    Purchase
    -0.36
    POSITIVE LOGITS
    ped
    0.49
    omed
    0.49
    pir
    0.48
    ishly
    0.48
    vered
    0.48
    lic
    0.47
    alled
    0.47
    hed
    0.47
    bled
    0.46
    ims
    0.45
    Activations Density 0.791%

    No Known Activations