© 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. 4-RES-JB
    11. 9680
    Prev
    Next
    INDEX
    Explanations

    references to bus-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to buses and bus transportation

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

    No Comments

    Negative Logits
     Martial
    -0.75
    sson
    -0.74
    vironment
    -0.69
     marrow
    -0.65
     Centauri
    -0.62
     Pharaoh
    -0.62
    aneous
    -0.61
    atio
    -0.60
    arial
    -0.59
    theless
    -0.59
    POSITIVE LOGITS
    loads
    1.17
    load
    1.02
    hel
    0.96
    boys
    0.87
     buses
    0.86
    boy
    0.84
    hy
    0.80
    INESS
    0.80
     DeL
    0.77
    dump
    0.77
    Activations Density 0.012%

    No Known Activations