© 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. 1-RES-JB
    11. 16081
    Prev
    Next
    INDEX
    Explanations

    mentions of award-winning achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to award-winning achievements in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omach
    -0.69
    ugu
    -0.68
     layers
    -0.66
    umm
    -0.66
    inges
    -0.66
     singled
    -0.64
    alle
    -0.63
    elo
    -0.63
     minors
    -0.61
     pores
    -0.60
    POSITIVE LOGITS
    winning
    0.89
    @@@@@@@@
    0.86
    ãĤ¦ãĤ¹
    0.81
    ãĥ³ãĤ¸
    0.78
    Initialized
    0.77
    iculture
    0.77
    isine
    0.75
    wright
    0.73
    theless
    0.73
     Pulitzer
    0.73
    Activations Density 0.024%

    No Known Activations