© 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. 9286
    Prev
    Next
    INDEX
    Explanations

    references to incoming individuals or things

    oai_token-act-pair · gpt-3.5-turbo

    the word "incoming" in various contexts, often relating to officials or information

    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
    ching
    -0.82
    FactoryReloaded
    -0.81
    Dur
    -0.77
    arist
    -0.74
    rolling
    -0.73
    arcity
    -0.72
    ARC
    -0.72
    mel
    -0.71
    ifling
    -0.69
    vet
    -0.69
    POSITIVE LOGITS
     incoming
    1.07
     arrivals
    0.96
     freshmen
    0.88
     outgoing
    0.77
     guests
    0.77
     occupant
    0.76
     commissions
    0.75
     arrival
    0.74
     drafts
    0.74
     recruits
    0.72
    Activations Density 0.006%

    No Known Activations