© 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. 14722
    Prev
    Next
    INDEX
    Explanations

    words related to continuity or persistence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating continuation or addition

    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
    76561
    -0.93
    quickShipAvailable
    -0.62
    watching
    -0.60
     Simulator
    -0.60
    assembly
    -0.59
    forced
    -0.58
    forcing
    -0.56
    assemb
    -0.56
    checking
    -0.56
     Sahara
    -0.56
    POSITIVE LOGITS
     be
    1.42
     serve
    1.10
     prove
    1.07
     suffice
    1.06
     decide
    1.06
     recognise
    1.06
     allow
    1.05
     qualify
    1.05
     become
    1.04
     settle
    1.02
    Activations Density 0.154%

    No Known Activations