© 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. 12242
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a level or extent of something

    oai_token-act-pair · gpt-3.5-turbo

    modifiers indicating varying degrees of significance or extent

    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
    soDeliveryDate
    -0.69
    together
    -0.67
     RUN
    -0.63
    etsk
    -0.62
    active
    -0.61
    ices
    -0.60
    gets
    -0.60
    isks
    -0.60
    packages
    -0.58
     TRANS
    -0.58
    POSITIVE LOGITS
     extent
    2.00
     degree
    1.56
     detriment
    1.18
     effect
    1.07
     discredit
    0.98
     lesser
    0.97
     avail
    0.92
     extend
    0.92
     point
    0.91
    venge
    0.90
    Activations Density 0.079%

    No Known Activations