© 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. 10-RES-JB
    11. 14104
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement or involvement

    oai_token-act-pair · gpt-3.5-turbo

    words related to commercial and economic activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ched
    -0.66
    bite
    -0.64
     dece
    -0.64
     Bunny
    -0.63
     Cinderella
    -0.62
    ching
    -0.62
    gha
    -0.61
     Salvador
    -0.60
     Leopard
    -0.60
    vae
    -0.60
    POSITIVE LOGITS
    ittee
    1.45
    onsense
    1.42
    ittees
    1.36
    issions
    1.30
    itte
    1.27
    itted
    1.25
    ander
    1.25
    ittal
    1.20
    ission
    1.16
    otion
    1.13
    Activations Density 0.028%

    No Known Activations