© 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. 2-RES-JB
    11. 5457
    Prev
    Next
    INDEX
    Explanations

    special characters with specific Unicode values

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that may indicate formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.80
    ngth
    -0.80
     obser
    -0.79
     srf
    -0.79
     constitu
    -0.75
     nomine
    -0.75
    psey
    -0.75
     guiActiveUn
    -0.73
     eleph
    -0.72
     reluct
    -0.71
    POSITIVE LOGITS
    µ
    1.36
    ®
    0.96
    °
    0.96
    ¾
    0.92
    âĢł
    0.90
    ħ
    0.90
    oom
    0.90
    ·
    0.89
    ´
    0.89
    ¬
    0.87
    Activations Density 0.005%

    No Known Activations