© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 7976
    Prev
    Next
    INDEX
    Explanations

    identifiers such as codes, titles, and names

    oai_token-act-pair · gpt-3.5-turbo

    the letter "Y" and its various forms

    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
     fin
    -0.77
     wanting
    -0.62
    croft
    -0.59
     tr
    -0.57
     agendas
    -0.57
     techno
    -0.56
     bothered
    -0.56
     concussion
    -0.55
     intrusive
    -0.55
     unborn
    -0.54
    POSITIVE LOGITS
    Y
    3.79
    YP
    2.22
    YC
    2.15
    YS
    2.06
    YING
    2.02
    YR
    1.96
    YL
    1.96
    YE
    1.91
    YA
    1.89
    YD
    1.86
    Activations Density 0.014%

    No Known Activations