© 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. 10-RES-JB
    11. 10642
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or challenge

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to difficulty and challenges

    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
    afety
    -0.66
    erity
    -0.63
     Sands
    -0.63
     Sheep
    -0.62
    ERG
    -0.62
     Nationwide
    -0.61
     Stories
    -0.61
    padding
    -0.59
    plates
    -0.59
    ness
    -0.58
    POSITIVE LOGITS
     quantify
    1.19
     obtain
    1.12
     comprehend
    1.11
     achieve
    1.11
     reconcile
    1.08
     navigate
    1.07
     manipulate
    1.05
     overcome
    1.05
     attain
    1.04
     accomplish
    1.01
    Activations Density 0.051%

    No Known Activations