INDEX

Explanations

negations or instances of the word "not."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 não

-0.77

not

-0.71

 nicht

-0.65

 ikke

-0.63

 không

-0.62

 tidak

-0.59

 Either

-0.58

Either

-0.56

not

-0.55

 niet

-0.53

POSITIVE LOGITS

 necessarily

1.10

yet

1.04

 only

0.96

tingham

0.89

yet

0.88

Yet

0.80

 seulement

0.78

orious

0.77

 even

0.77

Yet

0.76

Activations Density 0.367%

negations or instances of the word "not."

No Comments

No Known Activations