© 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. 3-RES-JB
    11. 1926
    Prev
    Next
    INDEX
    Explanations

    word stems related to the concept of being under pressure or constrained

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and past participles of verbs related to physical states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ********
    -0.76
    edia
    -0.74
    olog
    -0.71
    othy
    -0.70
     Rodham
    -0.70
    onomic
    -0.66
    album
    -0.66
    ocene
    -0.65
    rompt
    -0.63
    odox
    -0.63
    POSITIVE LOGITS
    veyard
    0.78
    pants
    0.75
    thood
    0.71
    xual
    0.65
    mma
    0.63
     Peaks
    0.62
    belt
    0.61
     thereof
    0.61
    enance
    0.61
    berry
    0.61
    Activations Density 0.016%

    No Known Activations