© 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. 7-RES-JB
    11. 20727
    Prev
    Next
    INDEX
    Explanations

    phrases related to the impact of events or decisions on specific entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" and its contextual uses in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifies
    -0.80
    owned
    -0.66
     according
    -0.66
    arate
    -0.65
    pers
    -0.65
    elaide
    -0.65
     depended
    -0.65
    strate
    -0.64
    HUD
    -0.63
     accordingly
    -0.63
    POSITIVE LOGITS
     slightest
    1.17
     onslaught
    1.17
     realities
    1.11
     entirety
    1.09
     sheer
    1.09
     impending
    1.05
     dangers
    1.03
     temptation
    1.02
     latest
    1.02
     complexities
    1.01
    Activations Density 0.388%

    No Known Activations