Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 18806
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to computer systems and their operations

    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
    Ò
    -0.94
    SHIP
    -0.80
    poons
    -0.79
    rez
    -0.79
    ody
    -0.74
    ricks
    -0.73
    axter
    -0.72
    henko
    -0.71
    otaur
    -0.71
    lot
    -0.67
    POSITIVE LOGITS
     clipboard
    0.95
     privileges
    0.93
    kernel
    0.90
     booted
    0.90
     privilege
    0.90
     password
    0.89
    Disk
    0.89
     administrator
    0.88
    Memory
    0.87
     directories
    0.87
    Activations Density 0.112%

    No Known Activations