© 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. 13040
    Prev
    Next
    INDEX
    Explanations

    aviation-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aviation and infrastructure

    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
    Beer
    -0.75
    女
    -0.69
     bitters
    -0.67
    ict
    -0.65
     Lives
    -0.64
    Scotland
    -0.63
    Leader
    -0.63
    hiro
    -0.62
    Rh
    -0.61
    Else
    -0.61
    POSITIVE LOGITS
     runway
    1.42
     airst
    0.93
    lane
    0.91
     carpet
    0.77
    selage
    0.77
     turbine
    0.75
    armac
    0.75
     clearance
    0.75
    vre
    0.74
    charg
    0.74
    Activations Density 0.005%

    No Known Activations