INDEX

Explanations

brand names or corporate entities

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

 onBind

-0.91

homonymie

-0.88

StoryboardSegue

-0.88

“…”

-0.87

 GenerationType

-0.84

 BoxFit

-0.84

skjaer

-0.83

ApplicationTests

-0.82

)</

-0.82

Vidite

-0.82

POSITIVE LOGITS

Pee

2.14

Pee

1.88

pee

0.82

pee

0.81

Bee

0.75

Cee

0.75

Bee

0.75

ing

0.73

DEE

0.71

Vee

0.70

Activations Density 0.000%

brand names or corporate entities

No Comments

No Known Activations