INDEX

Explanations

expressions of admiration and amazement

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Handlung

-0.51

 IndexPath

-0.50

хьтан

-0.50

 ModelExpression

-0.48

 referrerpolicy

-0.48

 InputDecoration

-0.48

 prescribe

-0.47



-0.46

itoriale

-0.46

IntoConstraints

-0.46

POSITIVE LOGITS

 amazed

1.01

 amazement

0.96

awe

0.89

 amaze

0.88

 astounding

0.86

 amazing

0.86

 astonishment

0.85

 astonished

0.81

 asomb

0.81

 astonishing

0.79

Activations Density 0.016%

expressions of admiration and amazement

No Comments

No Known Activations