© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    mentions of vehicles carrying something or someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "carrying."

    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
    ellen
    -0.84
    efer
    -0.70
    fortunately
    -0.69
    clair
    -0.68
    oxy
    -0.68
    Correct
    -0.66
    correct
    -0.66
    ################
    -0.66
     Creating
    -0.65
    IOR
    -0.64
    POSITIVE LOGITS
     capacity
    0.80
     lantern
    0.80
     capacities
    0.79
     carriers
    0.79
     crates
    0.76
     Boone
    0.74
     Capacity
    0.74
     containers
    0.73
     bundles
    0.72
     pige
    0.72
    Activations Density 0.010%

    No Known Activations