© 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. 7-RES-JB
    11. 11679
    Prev
    Next
    INDEX
    Explanations

    words related to design or design processes

    oai_token-act-pair · gpt-3.5-turbo

    references to "design."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICAN
    -0.76
    selves
    -0.76
     Lauder
    -0.75
    nikov
    -0.75
    ieri
    -0.74
     Sheen
    -0.74
     Adin
    -0.71
     Cele
    -0.69
     Thur
    -0.68
    Ton
    -0.68
    POSITIVE LOGITS
    ators
    1.08
    ator
    1.02
    ations
    0.96
    yout
    0.94
    ated
    0.91
    ating
    0.89
     design
    0.89
    ates
    0.86
     designs
    0.86
     flaw
    0.86
    Activations Density 0.047%

    No Known Activations