© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17013
    Prev
    Next
    INDEX
    Explanations

    phrases related to isolation or being alone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Lone" and references to solitude or solitary experiences

    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
    Ukraine
    -0.87
     Bulg
    -0.79
    uma
    -0.77
    rome
    -0.76
     Sakuya
    -0.76
     Ukrainians
    -0.75
    gif
    -0.73
    oice
    -0.71
    Drag
    -0.71
     Augusta
    -0.70
    POSITIVE LOGITS
     Lone
    2.49
     solitary
    1.47
    inker
    1.19
     lone
    1.18
    quin
    1.18
     Keen
    1.07
     Frem
    1.05
     berth
    1.05
     Leth
    1.04
     Jade
    1.02
    Activations Density 0.067%

    No Known Activations