© 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. 13372
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotional reactions or surprising events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to shock and surprise, particularly in contexts of emotional or physical reactions

    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
     Princ
    -0.66
    onymous
    -0.64
    uties
    -0.64
     Ascend
    -0.63
     Prospect
    -0.61
    ublic
    -0.61
     vain
    -0.60
     fathers
    -0.59
    apixel
    -0.59
    folios
    -0.58
    POSITIVE LOGITS
    wave
    1.45
    waves
    1.38
     absor
    1.29
    ingly
    1.12
    er
    1.08
    tro
    1.04
    crow
    0.86
     wave
    0.80
    ride
    0.78
    ers
    0.78
    Activations Density 0.053%

    No Known Activations