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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 22336
    Prev
    Next
    INDEX
    Explanations

    references to specific space-related terms, particularly names of rockets like Falcon 9 and Falcon 8

    oai_token-act-pair · gpt-3.5-turbo

    references to the Falcon 9 rocket and related technologies

    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
    asure
    -0.75
    laus
    -0.73
    ifact
    -0.72
    SPONSORED
    -0.71
    ODUCT
    -0.66
    asury
    -0.65
    ulhu
    -0.63
     detox
    -0.62
    ocrats
    -0.62
    cious
    -0.61
    POSITIVE LOGITS
     Falcon
    1.21
    Fal
    1.03
    hawk
    0.80
     Squadron
    0.79
    ress
    0.78
    wings
    0.78
    ers
    0.76
    resses
    0.76
    berries
    0.75
    ettes
    0.74
    Activations Density 0.006%

    No Known Activations