INDEX

Explanations

mentions of wire and its various forms and uses

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

 يتيمه

-0.72

SBATCH

-0.72

 Infórmanos

-0.70

ⓘ

-0.70

 Brix

-0.68

 bint

-0.67

 Juri

-0.66

rrggbb

-0.66

 Belk

-0.65

HandlerContext

-0.65

POSITIVE LOGITS

 wire

1.20

 alambre

1.04

wire

1.02

 Wire

0.96

Wire

0.95

 WIRE

0.92

 Draht

0.91

WIRE

0.90

 wires

0.84

 metal

0.67

Activations Density 0.004%

mentions of wire and its various forms and uses

No Comments

No Known Activations