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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6948
    Prev
    Next
    INDEX
    Explanations

    phrases indicating determination, perseverance, and focus on progress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reply
    -0.57
    oller
    -0.56
    OUR
    -0.56
    âĹ¼
    -0.56
    UP
    -0.54
    BACK
    -0.53
    ashtra
    -0.53
    rolet
    -0.53
    ajor
    -0.52
     unlaw
    -0.52
    POSITIVE LOGITS
    piring
    1.08
    pired
    1.07
     opposed
    1.07
    pires
    1.01
     well
    1.00
     evidenced
    0.98
    bestos
    0.96
     regards
    0.96
    ylum
    0.95
    phalt
    0.94
    Activations Density 0.259%

    No Known Activations