© 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. 9-RES-JB
    11. 2891
    Prev
    Next
    INDEX
    Explanations

    past-tense verbs related to negative events or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative events or conditions involving harm or damage

    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
    ecause
    -0.85
    ̶
    -0.78
    Ô
    -0.71
    ³³³³³³³³³³³³³³³³
    -0.71
    obbies
    -0.69
    olkien
    -0.69
    akespeare
    -0.67
    philis
    -0.67
    zbollah
    -0.67
     coli
    -0.66
    POSITIVE LOGITS
     portion
    1.16
     contents
    0.94
     trio
    0.93
     entity
    0.92
     thing
    0.92
     process
    0.89
     arrangement
    0.87
    ness
    0.87
     outcome
    0.86
     version
    0.85
    Activations Density 0.250%

    No Known Activations