© 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. 17762
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for instances of the word "going" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "going" in various contexts

    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
     Horus
    -0.79
    ullah
    -0.69
    unc
    -0.69
    fold
    -0.65
    chery
    -0.63
    ividually
    -0.62
    rehens
    -0.61
    cipl
    -0.61
    boxing
    -0.60
    cia
    -0.60
    POSITIVE LOGITS
    Ń·
    0.98
     rall
    0.78
    ãĥ£
    0.77
     bankrupt
    0.69
     GREEN
    0.67
    externalActionCode
    0.66
    lems
    0.66
    ãĤĭ
    0.66
    estone
    0.66
     sour
    0.65
    Activations Density 0.054%

    No Known Activations