© 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. 9-RES-JB
    6. 17876
    Prev
    Next
    INDEX
    Explanations

    mentions of anticipated outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    the letter 's' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Britons
    -0.60
     Rebell
    -0.57
     Continental
    -0.56
     WARN
    -0.55
    roit
    -0.54
     attaches
    -0.53
     Tours
    -0.53
     Imagine
    -0.53
     Resort
    -0.53
    assisted
    -0.52
    POSITIVE LOGITS
    omething
    1.01
     plenty
    0.92
     been
    0.84
     nothing
    0.84
     gotta
    0.81
    ometimes
    0.77
    been
    0.76
     somew
    0.76
    little
    0.75
     alot
    0.75
    Activations Density 0.031%

    No Known Activations