© 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. 6-RES-JB
    11. 13700
    Prev
    Next
    INDEX
    Explanations

    phrases related to loss or defeat

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to" followed by a number or a related concept indicating loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    handled
    -0.74
    ahime
    -0.70
    pring
    -0.67
    chini
    -0.66
    ended
    -0.66
    igr
    -0.64
    alore
    -0.63
    igrated
    -0.63
    spir
    -0.63
    cube
    -0.62
    POSITIVE LOGITS
     accommodate
    0.94
     fend
    0.89
     appease
    0.85
     compensate
    0.79
    othy
    0.79
     overcome
    0.77
     avoid
    0.76
     protect
    0.76
     satisfy
    0.74
     ensure
    0.74
    Activations Density 0.148%

    No Known Activations