© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21542
    Prev
    Next
    INDEX
    Explanations

    words related to technology terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to specific roles, activities, and measurements in various contexts

    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
    azaki
    -0.72
    enhagen
    -0.70
    reditary
    -0.65
    ģĸ
    -0.64
     skelet
    -0.64
    gage
    -0.62
    spring
    -0.61
    į
    -0.59
    etheless
    -0.58
    Ļ½
    -0.58
    POSITIVE LOGITS
    lihood
    0.65
    qqa
    0.60
    xual
    0.60
     itself
    0.59
    ashtra
    0.58
     alike
    0.58
     oneself
    0.58
     hereby
    0.57
     origin
    0.56
     yourselves
    0.55
    Activations Density 0.451%

    No Known Activations