© 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. 3-RES-JB
    11. 15216
    Prev
    Next
    INDEX
    Explanations

    phrases related to containers like cans, bags, crates, and buckets

    oai_token-act-pair · gpt-3.5-turbo

    references to containers, specifically cans and bags

    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
    Leader
    -0.70
    gh
    -0.69
    Synopsis
    -0.68
    te
    -0.68
    Phys
    -0.68
    âĸ¬
    -0.65
    oÄŁ
    -0.65
    ERAL
    -0.64
    ALLY
    -0.63
    liest
    -0.63
    POSITIVE LOGITS
    mith
    1.34
    paces
    1.27
    poons
    1.25
    hops
    1.23
    ourcing
    1.09
    uggest
    1.08
    etting
    1.07
    hips
    1.07
    ynthesis
    1.06
    ongs
    1.05
    Activations Density 0.078%

    No Known Activations