© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15315
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of level, such as "level of arrogance" or "level of engagement."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating varying degrees of intensity or measurement

    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
    enegger
    -0.87
    nesday
    -0.67
    Beast
    -0.67
    orial
    -0.67
    ãĥĹ
    -0.65
     Cyborg
    -0.65
     Andromeda
    -0.64
     Rounds
    -0.64
    è¦ļéĨĴ
    -0.63
    LM
    -0.63
    POSITIVE LOGITS
     crossings
    0.85
     assurance
    0.77
    lining
    0.74
    xual
    0.73
     levels
    0.72
     difference
    0.71
     distinctions
    0.70
     attainment
    0.68
    ropri
    0.66
     elevation
    0.66
    Activations Density 0.039%

    No Known Activations