© 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 EvalsExportsinterp-engineNEWAPI 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. 15216
    Prev
    Next
    INDEX
    Explanations

    statements made by or about people in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to people and their actions or characteristics

    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
    Leaks
    -0.57
     Collider
    -0.53
    STAR
    -0.53
    ð
    -0.52
     Vulkan
    -0.52
    Xi
    -0.51
     pandemonium
    -0.50
    Alright
    -0.49
    âĶĢâĶĢâĶĢâĶĢ
    -0.49
    OSP
    -0.49
    POSITIVE LOGITS
     themselves
    0.57
     sexes
    0.52
     retirees
    0.52
     persecuted
    0.51
     kindred
    0.51
     spouses
    0.51
     nests
    0.50
    agna
    0.50
     chained
    0.50
    exempt
    0.50
    Activations Density 3.410%

    No Known Activations