© 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. 19506
    Prev
    Next
    INDEX
    Explanations

    references to "pod," which may indicate various contexts such as technology, medical devices, or even marine biology

    oai_token-act-pair · gpt-3.5-turbo

    references to "pod" 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
     WARN
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    inventoryQuantity
    -0.69
    ãĤ¤ãĥĪ
    -0.69
    FUL
    -0.68
    listed
    -0.66
    ãĤ´ãĥ³
    -0.64
    âĸ¬
    -0.63
    ACA
    -0.61
    å°Ĩ
    -0.61
    POSITIVE LOGITS
     Pod
    1.22
    pod
    1.08
    iatric
    1.04
    esta
    1.04
    casters
    1.03
    caster
    1.03
     pod
    0.98
    omatic
    0.83
     pods
    0.82
    asus
    0.81
    Activations Density 0.009%

    No Known Activations