© 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. 22647
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives related to causing harm or damage

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to negative impacts or harm to various situations or entities

    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
    DragonMagazine
    -0.74
    mad
    -0.65
     consulted
    -0.63
    finder
    -0.60
     Unknown
    -0.56
     exercised
    -0.55
    gins
    -0.55
     INCLUD
    -0.54
     topped
    -0.53
     TBA
    -0.53
    POSITIVE LOGITS
     havoc
    1.06
     morale
    0.91
    ¿½
    0.72
     unwanted
    0.70
     unnecess
    0.70
     productivity
    0.69
    imize
    0.68
    rade
    0.67
     valuable
    0.67
     immersion
    0.66
    Activations Density 0.287%

    No Known Activations