© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11680
    Prev
    Next
    INDEX
    Explanations

    phrases related to excessive or extreme states

    oai_token-act-pair · gpt-3.5-turbo

    references to excessive or inflated conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Juliet
    -0.73
    ulhu
    -0.71
     RU
    -0.64
     Bravo
    -0.61
     Dynamics
    -0.60
     onward
    -0.60
     dime
    -0.60
     THR
    -0.59
     Dimension
    -0.59
     Patricia
    -0.59
    POSITIVE LOGITS
    arching
    1.40
    sized
    1.27
    emphasis
    1.22
    sam
    1.19
    the
    1.19
    represented
    1.19
    exc
    1.17
    optim
    1.13
    budget
    1.13
    expl
    1.11
    Activations Density 0.023%

    No Known Activations