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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 17806
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or objects, particularly cabins and cockpits

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of enclosed spaces, particularly cabins and cockpits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wrestling
    -0.78
    wu
    -0.73
    utenberg
    -0.70
    orus
    -0.70
    ranked
    -0.69
    undo
    -0.68
     Levy
    -0.67
     Wit
    -0.66
    ÏĦ
    -0.66
     Zer
    -0.66
    POSITIVE LOGITS
     cabin
    3.78
     Cabin
    2.65
     cockpit
    2.50
     compartment
    1.60
     hangar
    1.29
     cab
    1.28
     hut
    1.25
     cottage
    1.24
     lounge
    1.21
    selage
    1.16
    Activations Density 0.018%

    No Known Activations