© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3605
    Prev
    Next
    INDEX
    Explanations

    words related to intense reactions or surprising events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shock" and related phrases emphasizing its impact

    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
    uties
    -0.73
    iffin
    -0.66
    atively
    -0.65
    ichick
    -0.64
    umbers
    -0.64
    tein
    -0.63
    allery
    -0.62
     vain
    -0.61
    SHIP
    -0.60
    amins
    -0.60
    POSITIVE LOGITS
    wave
    1.45
    waves
    1.34
     absor
    1.17
    ingly
    1.05
    tro
    0.99
    er
    0.89
    crow
    0.87
     wave
    0.81
    pson
    0.79
    imaru
    0.77
    Activations Density 0.055%

    No Known Activations