© 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. 9-RES-JB
    11. 6160
    Prev
    Next
    INDEX
    Explanations

    phrases related to innovation and advancement

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to innovation and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ammo
    -0.56
    inventoryQuantity
    -0.56
     towed
    -0.55
    asma
    -0.54
    rake
    -0.53
     claimant
    -0.52
     Alv
    -0.52
     issuer
    -0.52
     spirited
    -0.51
     sided
    -0.51
    POSITIVE LOGITS
     unimaginable
    1.05
     hitherto
    1.05
     sorely
    1.01
     otherwise
    0.97
     never
    0.97
     seldom
    0.96
     unheard
    0.96
    cedented
    0.92
     normally
    0.91
    never
    0.90
    Activations Density 0.458%

    No Known Activations