© 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. 23217
    Prev
    Next
    INDEX
    Explanations

    information related to airplane flights

    oai_token-act-pair · gpt-3.5-turbo

    references to specific flights

    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
    itol
    -0.69
    âĶĢâĶĢ
    -0.69
    女
    -0.66
    ãĥ¤
    -0.65
    aido
    -0.65
    izont
    -0.63
     Haram
    -0.63
    putable
    -0.63
    ortium
    -0.63
    umen
    -0.63
    POSITIVE LOGITS
     flight
    1.11
     Flight
    1.10
     flights
    1.10
    plane
    0.98
    crew
    0.90
    planes
    0.89
     attendants
    0.89
    Flight
    0.89
    pread
    0.86
     Airlines
    0.86
    Activations Density 0.013%

    No Known Activations