INDEX

Explanations

programming-related terms and specific coding constructs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

чения

-0.51

-0.50

him

-0.48

렀

-0.47

PrototypeOf

-0.45

or

-0.44

-0.43

 that

-0.43

-0.42

 jardin

-0.42

POSITIVE LOGITS

ContentAsync

0.86

parsedMessage

0.85

 ſeveral

0.83

ⓧ

0.82

PreferredItem

0.82

UnsafeEnabled

0.81

 GenerationType

0.80

 becauſe

0.79

)");

0.77

 Theſe

0.76

Activations Density 1.499%

programming-related terms and specific coding constructs

No Comments

No Known Activations