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. 6-RES-JB
    6. 6464
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and resolutions

    oai_token-act-pair · gpt-3.5-turbo

    intent to take action or deliver commands

    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
    Downloadha
    -0.85
     strikingly
    -0.74
    quartered
    -0.71
     controvers
    -0.64
     famously
    -0.64
     notoriously
    -0.63
     allegedly
    -0.61
     recently
    -0.59
    ected
    -0.58
     dubbed
    -0.57
    POSITIVE LOGITS
     tomorrow
    1.12
     â̦"
    0.96
     ..."
    0.96
     someday
    0.95
    !"
    0.94
     fuckin
    0.87
     yourselves
    0.87
     myself
    0.86
    morrow
    0.85
    !'"
    0.85
    Activations Density 1.079%

    No Known Activations