© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11167
    Prev
    Next
    INDEX
    Explanations

    phrases relating to urgency or quick action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions taken in comparison to other actions or circumstances

    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
    eor
    -0.75
    rol
    -0.66
    ople
    -0.66
    rous
    -0.65
    oller
    -0.62
    roads
    -0.61
    rolet
    -0.60
    itiveness
    -0.60
    OUS
    -0.59
    amac
    -0.59
    POSITIVE LOGITS
     opposed
    1.24
     well
    1.13
    ynchron
    1.08
     soon
    1.00
    well
    0.94
    phy
    0.90
     evidenced
    0.90
    part
    0.90
    pired
    0.88
    under
    0.86
    Activations Density 0.211%

    No Known Activations