© 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. 2-RES-JB
    11. 15995
    Prev
    Next
    INDEX
    Explanations

    terms related to decay, degradation, or reduction

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to decay and degradation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --------------------------------------------------------
    -0.70
    ocular
    -0.70
    MN
    -0.69
    AMI
    -0.69
    orney
    -0.67
    Ey
    -0.67
    onga
    -0.66
    idav
    -0.66
    arag
    -0.66
    Hyper
    -0.65
    POSITIVE LOGITS
     decay
    1.41
     Decay
    0.99
    gradation
    0.98
    hyde
    0.90
     contag
    0.87
     dismant
    0.86
    cember
    0.83
     resil
    0.83
     curves
    0.79
    hower
    0.78
    Activations Density 0.006%

    No Known Activations