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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21667
    Prev
    Next
    INDEX
    Explanations

    words related to objectivity, objects, and objectification

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "objects" in various contexts

    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
    fer
    -0.74
    DAY
    -0.73
    ornia
    -0.73
    NPR
    -0.72
    forth
    -0.68
    coni
    -0.67
    bred
    -0.67
    burg
    -0.66
    ndra
    -0.65
    heit
    -0.65
    POSITIVE LOGITS
    ivity
    1.06
    ivist
    1.02
    ivism
    0.94
    ives
    0.94
     lesson
    0.93
     perman
    0.92
    ively
    0.90
    ification
    0.87
    imus
    0.84
    ellery
    0.83
    Activations Density 0.035%

    No Known Activations