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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19480
    Prev
    Next
    INDEX
    Explanations

    scientific disciplines and academic positions, specifically focusing on engineering and biology-related fields

    oai_token-act-pair · gpt-3.5-turbo

    academic subjects and fields of study related to science and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.72
    inventoryQuantity
    -0.71
    ãĥİ
    -0.71
    20439
    -0.68
    çĦ
    -0.67
     calendars
    -0.67
     Valkyrie
    -0.65
     greet
    -0.65
     informants
    -0.64
    MSN
    -0.63
    POSITIVE LOGITS
     Sciences
    0.99
     Cornell
    0.97
     Harvard
    0.93
     sciences
    0.92
     professor
    0.88
     doctoral
    0.84
     PhD
    0.83
     emer
    0.83
    ournals
    0.83
     UCLA
    0.82
    Activations Density 0.077%

    No Known Activations