© 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. 8557
    Prev
    Next
    INDEX
    Explanations

    keywords related to success and achievement

    oai_token-act-pair · gpt-3.5-turbo

    themes related to success and achievement

    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
     backdrop
    -0.62
     monop
    -0.62
     dispute
    -0.62
     rout
    -0.60
    ãĤ¦ãĤ¹
    -0.59
     bluff
    -0.58
     pity
    -0.58
     arra
    -0.57
     bribe
    -0.57
     targ
    -0.56
    POSITIVE LOGITS
     academ
    1.03
     someday
    1.00
     athlet
    0.96
     creatively
    0.93
     financially
    0.91
     regardless
    0.89
     together
    0.88
     anew
    0.88
     exponentially
    0.87
     professionally
    0.85
    Activations Density 0.316%

    No Known Activations