Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 21378
    Prev
    Next
    INDEX
    Explanations

    references to specific airlines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of airline companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢ
    -0.80
    liest
    -0.77
     Schne
    -0.67
    SPONSORED
    -0.66
    obj
    -0.66
     Jah
    -0.64
     motions
    -0.64
    arist
    -0.63
    ebook
    -0.62
    nered
    -0.62
    POSITIVE LOGITS
     Airlines
    1.16
     Plaza
    0.90
    ports
    0.85
    otive
    0.84
     Holdings
    0.83
     Airways
    0.82
     Lounge
    0.81
    Pass
    0.80
    daq
    0.80
     Stores
    0.77
    Activations Density 0.022%

    No Known Activations