© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1337
    Prev
    Next
    INDEX
    Explanations

    specific names, abbreviations, and terms, possibly related to a particular context or field of interest

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms, particularly relating to positions or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erity
    -0.77
    ãĤ¹ãĥĪ
    -0.76
    adeon
    -0.73
     dism
    -0.73
    Downloadha
    -0.69
     Crom
    -0.68
    tta
    -0.66
    ²
    -0.66
    ielding
    -0.63
     reproduce
    -0.62
    POSITIVE LOGITS
     PF
    2.88
     OT
    2.29
     OG
    1.53
     SG
    1.19
     PTS
    1.16
     JC
    1.08
     OL
    1.07
     EG
    1.01
     RHP
    0.93
     PB
    0.91
    Activations Density 0.018%

    No Known Activations