© 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. 2-RES-JB
    11. 4511
    Prev
    Next
    INDEX
    Explanations

    phrases related to being under some kind of influence or control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "under" with varying modifiers often related to conditions or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extrad
    -0.69
    wl
    -0.65
     hereafter
    -0.62
    ATIVE
    -0.62
    bernatorial
    -0.61
    ioxide
    -0.60
    eln
    -0.60
    ewitness
    -0.59
     testify
    -0.59
     mov
    -0.58
    POSITIVE LOGITS
    neath
    1.09
    under
    1.05
    standing
    0.98
    stood
    0.89
    blind
    0.88
    comings
    0.87
    und
    0.86
    cuts
    0.85
    pins
    0.85
    lying
    0.84
    Activations Density 0.007%

    No Known Activations