© 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. 9311
    Prev
    Next
    INDEX
    Explanations

    terms related to transportation and movement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transportation and movement

    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
    NVIDIA
    -0.69
    andal
    -0.68
    Pin
    -0.66
    Enough
    -0.66
    endra
    -0.65
    ellen
    -0.65
    uster
    -0.63
    brand
    -0.63
    put
    -0.62
    ENA
    -0.62
    POSITIVE LOGITS
     receipts
    0.93
     shipments
    0.88
     deliveries
    0.86
    ship
    0.82
     carriers
    0.81
     arrivals
    0.78
     visas
    0.78
     destinations
    0.77
    engers
    0.77
    ience
    0.76
    Activations Density 0.115%

    No Known Activations