© 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. 12825
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of pouring

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pour" and its variations, indicating a focus on liquid transfer or influx

    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
    nesota
    -0.71
    ALE
    -0.68
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    ization
    -0.66
    nton
    -0.66
    isation
    -0.65
    leigh
    -0.64
     Nanto
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    izons
    -0.62
    POSITIVE LOGITS
     encour
    1.12
     poured
    1.11
     pouring
    1.05
     pour
    0.86
    pour
    0.82
     buckets
    0.81
     boiling
    0.78
     overfl
    0.77
     bleach
    0.76
     flowed
    0.72
    Activations Density 0.011%

    No Known Activations