© 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. 8-RES-JB
    11. 6951
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and measurements, such as pH, thickness, length, density, brightness, diameter, strength, and aperture

    oai_token-act-pair · gpt-3.5-turbo

    measurements and specifications related to pH, density, brightness, and physical dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bara
    -0.81
    ovie
    -0.76
    JECT
    -0.74
    odon
    -0.72
    lando
    -0.71
    roma
    -0.71
    vous
    -0.70
    ĪĴ
    -0.68
    amar
    -0.68
    habi
    -0.68
    POSITIVE LOGITS
     ranges
    1.07
     measurement
    1.05
     difference
    1.01
     gradient
    1.00
     tolerance
    0.98
     estimation
    0.97
     fluctuations
    0.97
     coefficient
    0.95
     determination
    0.94
     range
    0.93
    Activations Density 0.208%

    No Known Activations