INDEX

Explanations

patterns related to variable declarations and definitions in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Fourth

-0.98

Fourth

-0.96

 four

-0.91

 fourth

-0.91

fourth

-0.88

 Monday

-0.83

 ninth

-0.83

-0.80

 FOUR

-0.79

 fifth

-0.78

POSITIVE LOGITS

1.13

 صوتيه

0.64

setVerticalGroup

0.56

 HasFactory

0.56

❉

0.51

 Perkin

0.50

setPointSize

0.50

 toit

0.49

tula

0.48

Портал

0.47

Activations Density 0.136%

patterns related to variable declarations and definitions in programming

No Comments

No Known Activations