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. 23501
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of spreading or promoting information or ideas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "propagation" and adherence to certain standards or expectations

    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
    epad
    -0.76
    claw
    -0.74
     flair
    -0.74
    uyomi
    -0.73
    addon
    -0.73
     Trevor
    -0.72
     perk
    -0.72
     Wonder
    -0.72
     Heath
    -0.70
     retake
    -0.69
    POSITIVE LOGITS
     propag
    2.13
     propagate
    2.01
     propagation
    1.74
     conform
    1.52
     spatial
    1.38
     invari
    1.25
     temporal
    1.19
     behaved
    1.18
     transient
    1.12
     degraded
    1.11
    Activations Density 0.093%

    No Known Activations