© 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. 7-RES-JB
    11. 21074
    Prev
    Next
    INDEX
    Explanations

    mentions of loss or decreasing in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lose" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sis
    -0.77
    gon
    -0.67
    Released
    -0.65
     Janeiro
    -0.64
     primed
    -0.62
    agher
    -0.61
    INO
    -0.61
     prov
    -0.61
    ature
    -0.59
     pleased
    -0.58
    POSITIVE LOGITS
     aversion
    0.81
     sight
    0.79
     virginity
    0.78
     souls
    0.76
    touch
    0.75
     Souls
    0.74
    luster
    0.74
    ittens
    0.71
     credibility
    0.71
     limbs
    0.71
    Activations Density 0.039%

    No Known Activations