© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 3993
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to computer networks

    oai_token-act-pair · gpt-3.5-turbo

    references to networking concepts and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.67
    inse
    -0.66
    Child
    -0.65
    ena
    -0.65
    UES
    -0.65
     hers
    -0.63
    OPLE
    -0.63
    VEL
    -0.63
    Tre
    -0.63
    nant
    -0.62
    POSITIVE LOGITS
     network
    1.08
     networks
    1.04
     connectivity
    1.02
     networking
    0.95
     Networks
    0.91
     connection
    0.91
    network
    0.85
     footprint
    0.84
     connections
    0.83
     architectures
    0.82
    Activations Density 0.021%

    No Known Activations