© 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. 7-RES-JB
    11. 7506
    Prev
    Next
    INDEX
    Explanations

    phrases related to supply chain management

    oai_token-act-pair · gpt-3.5-turbo

    references to supply chains and their related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.71
    NL
    -0.70
    pelled
    -0.69
    paren
    -0.69
     Pengu
    -0.64
    Rail
    -0.64
    drawn
    -0.64
    toc
    -0.62
     BALL
    -0.62
    lar
    -0.62
    POSITIVE LOGITS
     continuum
    0.84
     specialization
    0.82
     sophistication
    0.73
    relevant
    0.70
     influencing
    0.69
     approaches
    0.69
    ologies
    0.68
     approach
    0.67
     architectures
    0.67
     optimization
    0.66
    Activations Density 0.291%

    No Known Activations