© 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. 0-RES-JB
    11. 2225
    Prev
    Next
    INDEX
    Explanations

    words related to actions or concepts of enforcing or following specific policies or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ition," indicating a focus on terms related to processes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brooks
    -0.61
     com
    -0.61
     declines
    -0.59
     fed
    -0.56
     needle
    -0.55
     risks
    -0.55
     trough
    -0.54
     Gon
    -0.53
     covered
    -0.53
     CONTR
    -0.53
    POSITIVE LOGITS
    ition
    4.70
    itions
    3.33
    ITION
    2.67
    itious
    2.18
    itional
    2.04
    itionally
    1.88
    itive
    1.59
    itory
    1.42
    itives
    1.42
    itiveness
    1.33
    Activations Density 0.010%

    No Known Activations