© 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. 20316
    Prev
    Next
    INDEX
    Explanations

    phrases related to people or objects positioning or forming a line

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lined" and its variations, indicating a focus on queuing or arrangement

    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
    effic
    -0.68
     mathemat
    -0.67
    mpeg
    -0.61
    rant
    -0.60
    bler
    -0.60
    ination
    -0.60
    rl
    -0.60
    loss
    -0.59
    ibur
    -0.59
    context
    -0.58
    POSITIVE LOGITS
     up
    1.14
     shelves
    0.98
    up
    0.91
    Up
    0.87
    ups
    0.83
     Up
    0.77
    UP
    0.74
     ups
    0.71
    alled
    0.69
     floors
    0.69
    Activations Density 0.052%

    No Known Activations