© 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. 691
    Prev
    Next
    INDEX
    Explanations

    numeric values

    oai_token-act-pair · gpt-3.5-turbo

    references to numbers and phases in the context of processes or events

    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
    SOURCE
    -0.76
     Mehran
    -0.72
    href
    -0.71
    fax
    -0.71
    abase
    -0.68
    pload
    -0.68
    adobe
    -0.67
    Father
    -0.66
    Ô
    -0.64
    Earn
    -0.64
    POSITIVE LOGITS
     inference
    0.66
    ļéĨĴ
    0.65
    itaire
    0.65
    intensive
    0.65
    ħĭ
    0.64
     inhibitors
    0.64
     Implementation
    0.63
    arten
    0.63
     enhancement
    0.63
     suprem
    0.63
    Activations Density 0.341%

    No Known Activations