© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14147
    Prev
    Next
    INDEX
    Explanations

    terms related to a unifying concept or overarching category

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of an "umbrella" in various contexts, indicating a broad or inclusive theme or group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.89
    bos
    -0.79
    achy
    -0.78
    anooga
    -0.77
    nesota
    -0.75
    onew
    -0.70
    avery
    -0.68
    anche
    -0.68
    eming
    -0.68
    eral
    -0.67
    POSITIVE LOGITS
     umbrella
    1.13
     umb
    0.97
     cord
    0.75
     poles
    0.74
     blanket
    0.68
     canopy
    0.68
    iliary
    0.67
     applic
    0.67
    illary
    0.66
     wip
    0.66
    Activations Density 0.032%

    No Known Activations