© 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. 10572
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental actions or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government actions or policies

    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
     memory
    -0.75
     verbs
    -0.73
     headlights
    -0.72
     beads
    -0.72
     Miles
    -0.69
     Slip
    -0.68
     veins
    -0.67
     Ell
    -0.67
     Meadows
    -0.65
     Holt
    -0.65
    POSITIVE LOGITS
    funded
    1.81
    sponsored
    1.81
    approved
    1.80
    backed
    1.76
    controlled
    1.70
    issued
    1.70
    appointed
    1.66
    owned
    1.65
    supported
    1.64
    provided
    1.63
    Activations Density 0.058%

    No Known Activations