© 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. 9333
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronics and mechanics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technical components or systems, particularly in engineering or mechanics

    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
     HuffPost
    -0.73
     British
    -0.60
     Jah
    -0.59
    nos
    -0.59
     âĢº
    -0.59
    htaking
    -0.58
     Polit
    -0.58
     Dr
    -0.57
    Tre
    -0.57
    arak
    -0.56
    POSITIVE LOGITS
     destro
    0.76
    endif
    0.76
     laun
    0.74
    utenberg
    0.73
     rul
    0.73
    yang
    0.70
     equivalents
    0.68
    alogue
    0.68
     cubes
    0.67
     monop
    0.66
    Activations Density 0.820%

    No Known Activations