© 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. 4-RES-JB
    11. 11378
    Prev
    Next
    INDEX
    Explanations

    personal reflections and thoughts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and emotions

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

    No Comments

    Negative Logits
     Infrastructure
    -0.51
     multinational
    -0.50
     substantially
    -0.50
     incumbent
    -0.50
     Revenue
    -0.49
    quartered
    -0.48
     controvers
    -0.47
     mammoth
    -0.47
     nationally
    -0.46
     Regions
    -0.45
    POSITIVE LOGITS
     fuckin
    0.82
     fucking
    0.73
     bitch
    0.65
    -"
    0.65
     fucked
    0.64
    laughs
    0.63
     goddamn
    0.62
    fuck
    0.60
     somet
    0.59
     kinda
    0.59
    Activations Density 3.592%

    No Known Activations