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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 15200
    Prev
    Next
    INDEX
    Explanations

    words related to a negative attribute or deficiency in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the concept of absence or deficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.72
     Seal
    -0.61
     Petra
    -0.61
     Steps
    -0.58
     Dug
    -0.58
     Prin
    -0.56
     helicop
    -0.56
     Families
    -0.55
     Dial
    -0.54
     Robots
    -0.54
    POSITIVE LOGITS
    lust
    1.72
    luster
    1.48
     thereof
    1.37
    ada
    1.28
    lessly
    0.99
    adas
    0.97
     of
    0.93
    iveness
    0.85
    lest
    0.81
    ful
    0.81
    Activations Density 0.036%

    No Known Activations