© 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. 4-RES-JB
    11. 22176
    Prev
    Next
    INDEX
    Explanations

    verbs that imply focus or concentration

    oai_token-act-pair · gpt-3.5-turbo

    phrases that focus on the concept of being "centered" or "revolving" around a specific topic or issue

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

    No Comments

    Negative Logits
    gotten
    -0.71
    é¾įå
    -0.67
    ania
    -0.65
    ãģ®å
    -0.62
     ABE
    -0.61
    bie
    -0.61
    thur
    -0.60
    ãĤī
    -0.60
    ham
    -0.59
    mouth
    -0.59
    POSITIVE LOGITS
     centered
    0.98
    SHIP
    0.87
     revolving
    0.84
     revolves
    0.83
    ovie
    0.82
    rikes
    0.76
    olars
    0.74
    iosity
    0.72
    yrinth
    0.72
    uates
    0.72
    Activations Density 0.030%

    No Known Activations