© 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. 20761
    Prev
    Next
    INDEX
    Explanations

    words related to ideologies and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to ideologies and related concepts

    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
    FACE
    -0.91
     SEAL
    -0.76
    lain
    -0.70
    ARDS
    -0.70
    smith
    -0.70
    bucks
    -0.66
     Sands
    -0.66
    ILY
    -0.66
     disinfect
    -0.65
     Mercy
    -0.65
    POSITIVE LOGITS
    ologue
    1.02
    ī
    0.98
     ide
    0.90
    rix
    0.90
    mble
    0.90
     theoret
    0.89
    ality
    0.87
    ogly
    0.85
    iple
    0.83
    atorial
    0.83
    Activations Density 0.014%

    No Known Activations