© 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. 4-RES-JB
    11. 7063
    Prev
    Next
    INDEX
    Explanations

    measurements in terms of length and width

    oai_token-act-pair · gpt-3.5-turbo

    dimensions and measurements of objects

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

    No Comments

    Negative Logits
    Cash
    -0.73
    YN
    -0.72
    tag
    -0.71
     Yel
    -0.67
    cash
    -0.66
     Darling
    -0.65
    Tea
    -0.64
     Skydragon
    -0.63
    effects
    -0.63
    cit
    -0.63
    POSITIVE LOGITS
     diameter
    0.95
     gorilla
    0.84
    iameter
    0.82
    izont
    0.79
     height
    0.78
     carp
    0.77
     circumference
    0.77
     horizontally
    0.74
     hex
    0.73
     increments
    0.73
    Activations Density 0.060%

    No Known Activations