© 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. 8-RES-JB
    11. 7706
    Prev
    Next
    INDEX
    Explanations

    words related to surprising or shocking events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shock" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uties
    -0.68
    iffin
    -0.67
    ickr
    -0.65
     vain
    -0.65
    allery
    -0.63
     Starg
    -0.62
    oreal
    -0.62
    ial
    -0.61
    amins
    -0.61
    umbers
    -0.60
    POSITIVE LOGITS
    waves
    1.36
    wave
    1.33
     absor
    1.08
    ingly
    0.94
    ा
    0.88
    er
    0.83
    tro
    0.83
    imaru
    0.81
    crow
    0.79
     wave
    0.77
    Activations Density 0.038%

    No Known Activations