© 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. 10-RES-JB
    11. 3055
    Prev
    Next
    INDEX
    Explanations

    terms related to instructions or processes

    oai_token-act-pair · gpt-3.5-turbo

    processes and activities related to installation and execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geries
    -0.90
    arag
    -0.82
    ivic
    -0.77
    olen
    -0.67
    IFIED
    -0.67
    ened
    -0.63
    aceous
    -0.62
    pora
    -0.62
    oso
    -0.61
    ishly
    -0.61
    POSITIVE LOGITS
     method
    1.14
     process
    1.14
     mechanism
    1.11
     procedure
    1.10
     rate
    1.08
     methods
    1.07
     interval
    1.06
     sequence
    1.00
     technique
    1.00
     time
    0.98
    Activations Density 0.341%

    No Known Activations