© 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. 16575
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning equivalence or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe comparisons of equivalence

    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
    stal
    -0.69
    Äĩ
    -0.67
    avorite
    -0.66
    aina
    -0.65
    Cola
    -0.64
    ggles
    -0.64
    stant
    -0.63
    cker
    -0.63
    oho
    -0.62
    stra
    -0.62
    POSITIVE LOGITS
     amounts
    0.93
     sized
    0.90
     thereof
    0.87
     quantities
    0.86
    aneously
    0.85
     thereto
    0.84
     amount
    0.80
    ivalent
    0.78
     to
    0.75
     proportions
    0.73
    Activations Density 0.040%

    No Known Activations