© 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. 2-RES-JB
    11. 10419
    Prev
    Next
    INDEX
    Explanations

    terms related to significant events or important locations

    oai_token-act-pair · gpt-3.5-turbo

    references to "landmarks" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thia
    -0.87
    zona
    -0.77
    sis
    -0.75
    gans
    -0.74
    zie
    -0.74
    nesia
    -0.69
    sei
    -0.69
    anguage
    -0.68
    IDES
    -0.67
    á¹
    -0.67
    POSITIVE LOGITS
     landmark
    1.21
     landmarks
    0.95
     breakthrough
    0.74
     milestone
    0.73
    stones
    0.71
     achievement
    0.69
     glim
    0.67
     milestones
    0.66
     fixture
    0.66
    ãĤ¤ãĥĪ
    0.65
    Activations Density 0.006%

    No Known Activations