INDEX

Explanations

occurrences of the word "loop" and its variations in programming contexts

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

rosia

-0.52

bread

-0.52

Bread

-0.52

énéral

-0.51

หวัด

-0.51

妥

-0.51

showToast

-0.48

xã

-0.48

伍

-0.47

ίναι

-0.47

POSITIVE LOGITS

 loop

1.67

loop

1.55

 loops

1.45

Loop

1.41

 Loop

1.41

 Loops

1.28

 LOOP

1.23

loops

1.13

LOOP

1.11

 looping

1.10

Activations Density 0.027%

occurrences of the word "loop" and its variations in programming contexts

No Comments

No Known Activations