© 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. 3-RES-JB
    11. 3974
    Prev
    Next
    INDEX
    Explanations

    words related to philosophical ideologies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "idea" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FACE
    -0.99
    lain
    -0.75
    ding
    -0.75
    worthiness
    -0.72
    smith
    -0.69
    ARDS
    -0.68
    ICAN
    -0.66
     SEAL
    -0.65
    din
    -0.64
    RESULTS
    -0.64
    POSITIVE LOGITS
    mble
    0.99
     ide
    0.89
    ally
    0.88
     Ide
    0.88
    ologue
    0.84
    rix
    0.84
    agog
    0.80
    ividual
    0.78
     theoret
    0.78
    ality
    0.78
    Activations Density 0.013%

    No Known Activations