INDEX

Explanations

comparisons and equality expressions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-0.89

帖最后由

-0.84

 Majefty

-0.80

 ſtate

-0.79

 reaſon

-0.78

 purpoſe

-0.77

(;;)

-0.77

 Diſ

-0.74

 uſe

-0.73

 greateſt

-0.73

POSITIVE LOGITS

equalsIgnoreCase

0.77

 quick

0.74

equals

0.73

EQUALS

0.67

Equals

0.65

 quite

0.61

сто

0.60

て

0.57

 pretty

0.55

big

0.55

Activations Density 0.117%

comparisons and equality expressions in code

No Comments

No Known Activations