INDEX

Explanations

occurrences of the negation word "not" in various 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

 raiſ

-0.88

 fhew

-0.82

Efq

-0.80

 fevere

-0.79

 ſever

-0.76

 Sarm

-0.74

 ſeveral

-0.74

 pleaſure

-0.73

 uſed

-0.71

 feveral

-0.70

POSITIVE LOGITS

not

2.52

not

2.33

Not

2.22

NOT

2.13

Not

2.06

NOT

2.05

 nicht

1.34

isNot

1.23

 niet

1.22

nicht

1.17

Activations Density 0.222%

occurrences of the negation word "not" in various contexts

No Comments

No Known Activations