INDEX

Explanations

the word "not" in various forms and contexts to signal negation or disagreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Sardinia

-0.83

 ſever

-0.81

 fevere

-0.76

 ſche

-0.75

 Jefus

-0.75

 raiſ

-0.74

 itſelf

-0.72

 pleaſure

-0.72

 ſch

-0.71

 myſelf

-0.71

POSITIVE LOGITS

not

1.18

Not

1.11

NOT

0.99

isNot

0.95

not

0.92

Not

0.87

allowNull

0.80

NOT

0.80

RTDA

0.79

 niet

0.79

Activations Density 0.351%

the word "not" in various forms and contexts to signal negation or disagreement

No Comments

No Known Activations