INDEX

Explanations

instances of denial or uncertainty in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 even

-0.72

 invece

-0.70

 anche

-0.70

 both

-0.69

both

-0.65

 either

-0.61

 plutôt

-0.59

 Even

-0.59

even

-0.58

 incluso

-0.58

POSITIVE LOGITS

 itſelf

1.18

 myſelf

1.15

ſelf

1.04

 iſt

1.04

 ProtoMessage

1.02

 sondern

1.01

RectangleBorder

1.00

 themſelves

0.99

 pleaſure

0.98

 becauſe

0.97

Activations Density 0.139%

instances of denial or uncertainty in statements

No Comments

No Known Activations