© 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. 8-RES-JB
    6. 2480
    Prev
    Next
    INDEX
    Explanations

    references to numerical values enclosed in parentheses

    oai_token-act-pair · gpt-3.5-turbo

    opening and closing parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imposing
    -0.68
     imperson
    -0.66
     invari
    -0.66
     recording
    -0.66
     smugg
    -0.65
     vil
    -0.63
     diploma
    -0.63
     intellig
    -0.63
     Ferr
    -0.62
     maxim
    -0.62
    POSITIVE LOGITS
    *)
    1.27
    SourceFile
    1.22
    edited
    1.18
    +)
    1.14
    -)
    1.13
    ?)
    1.10
    tm
    1.05
    ...)
    1.00
    TM
    0.99
    ?),
    0.98
    Activations Density 0.038%

    No Known Activations