© 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. 11-RES-JB
    11. 17574
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or negative evaluation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that link complex ideas or themes

    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
    EStream
    -0.88
    culosis
    -0.85
    ynthesis
    -0.81
    rave
    -0.77
    onica
    -0.76
    vation
    -0.76
    SHIP
    -0.74
    heid
    -0.74
    oop
    -0.72
    ledged
    -0.71
    POSITIVE LOGITS
     unpredictable
    1.12
     devoid
    1.05
     prone
    1.05
     inaccessible
    1.04
     riddled
    1.04
     unreliable
    1.04
     ineffective
    1.04
     requires
    1.03
     incon
    1.03
     involves
    1.00
    Activations Density 0.123%

    No Known Activations