Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 15425
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a process

    oai_token-act-pair · gpt-3.5-turbo

    instructions or steps related to a process or system

    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
     attRot
    -0.77
    else
    -0.75
     regrets
    -0.73
     consequently
    -0.69
     likewise
    -0.68
    urther
    -0.67
    Others
    -0.67
     latter
    -0.66
    avoid
    -0.66
    Elsewhere
    -0.65
    POSITIVE LOGITS
     randomly
    0.91
     rectangle
    0.77
     outline
    0.77
     cardboard
    0.76
     rectangular
    0.76
     random
    0.74
     predetermined
    0.74
     dataset
    0.72
     folder
    0.71
     sheet
    0.71
    Activations Density 0.592%

    No Known Activations