© 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. 10-RES-JB
    11. 16535
    Prev
    Next
    INDEX
    Explanations

    names of people or entities as subjects of actions

    oai_token-act-pair · gpt-3.5-turbo

    connections and references to specific entities or names

    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
    CE
    -0.99
     CE
    -0.90
    PE
    -0.90
    EU
    -0.87
    eely
    -0.79
    Google
    -0.78
     ly
    -0.78
    325
    -0.78
    LE
    -0.78
    ELY
    -0.76
    POSITIVE LOGITS
     Mull
    1.27
     Mall
    1.14
     Mug
    1.10
     Barb
    1.10
     Port
    1.05
     Loft
    1.02
     Jack
    0.99
     Skull
    0.96
     mug
    0.93
     Bung
    0.93
    Activations Density 0.556%

    No Known Activations