© 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. 9-RES-JB
    11. 16009
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abstraction and commodification of concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to commodification and loss of authenticity

    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
     recommend
    -0.78
     recommending
    -0.78
    Bench
    -0.77
     recommends
    -0.77
    Recommend
    -0.76
     FY
    -0.75
    charges
    -0.74
     MPH
    -0.73
    recomm
    -0.72
    ospons
    -0.72
    POSITIVE LOGITS
     alienated
    1.30
     alienation
    1.26
     masculinity
    1.16
     dehuman
    1.14
     femin
    1.10
    illusion
    1.08
     hegemony
    1.05
     caricature
    1.00
     adolescence
    1.00
     emanc
    1.00
    Activations Density 1.678%

    No Known Activations