© 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. 9-RES-JB
    11. 7290
    Prev
    Next
    INDEX
    Explanations

    phrases related to compensating for something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to compensating or making up for losses or deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onomy
    -0.72
    eks
    -0.69
    eki
    -0.65
    ryu
    -0.64
    FTWARE
    -0.62
     inquire
    -0.61
    chief
    -0.61
     Dreams
    -0.61
    aka
    -0.61
    7601
    -0.60
    POSITIVE LOGITS
     lost
    1.18
     losses
    1.17
     deficiencies
    1.12
     shortfall
    1.11
     shortcomings
    1.01
     loss
    0.97
     missing
    0.96
     deficiency
    0.95
    missing
    0.94
     gaps
    0.94
    Activations Density 0.153%

    No Known Activations