© 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. 4-RES-JB
    11. 10870
    Prev
    Next
    INDEX
    Explanations

    phrases prompting for opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    questions prompting opinions or thoughts

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

    No Comments

    Negative Logits
    devices
    -0.77
    clad
    -0.72
    abb
    -0.69
    aid
    -0.68
    ague
    -0.67
     Adin
    -0.66
    announced
    -0.66
    ortunately
    -0.65
    ancers
    -0.65
    translation
    -0.64
    POSITIVE LOGITS
     regret
    0.83
    IUM
    0.76
    zai
    0.75
    ij士
    0.73
    ventus
    0.72
    itia
    0.71
     impeachment
    0.71
     aloud
    0.70
    rison
    0.69
     provoking
    0.69
    Activations Density 0.050%

    No Known Activations