INDEX

Explanations

words related to specific medical conditions or terms

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

 Roskov

-0.73

ritch

-0.70

 secours

-0.70

cipient

-0.66

 matières

-0.66

ING

-0.65

 Lightfoot

-0.64

 løs

-0.64

 circulaire

-0.64

 diputados

-0.63

POSITIVE LOGITS

ennes

1.99

 שוליים

1.27

 Fenne

1.10

 createStore

1.05

yntaxException

0.99

 Renner

0.96

 يتيمه

0.94

 Kenney

0.93

 GenerationType

0.93

ContentAsync

0.84

Activations Density 0.000%

words related to specific medical conditions or terms

No Comments

No Known Activations