© 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. 10-RES-JB
    11. 10573
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions taken or decisions made by multiple individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or behaviors associated with groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EVEN
    -0.63
    IFIED
    -0.61
    Uh
    -0.59
    Journal
    -0.59
    odor
    -0.58
     Declaration
    -0.58
    Luck
    -0.58
     Invisible
    -0.58
    Hum
    -0.58
     Bash
    -0.57
    POSITIVE LOGITS
     prepares
    1.16
     relates
    1.07
     transitions
    1.02
     progresses
    0.95
     strives
    0.95
     relate
    0.94
     transitioned
    0.93
     seeks
    0.92
     recovers
    0.91
     prepare
    0.90
    Activations Density 0.092%

    No Known Activations