INDEX

Explanations

terms related to various scientific and medical contexts, particularly focusing on faith, taxation, and biological markers

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

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

↵

-0.41

Transfer

-0.40

Object

-0.40

Persist

-0.38

↵↵

-0.38

 flore

-0.37

<strong>

-0.37

ены

-0.37

 siyah

-0.36

transferase

-0.36

POSITIVE LOGITS

 فريبيس

1.11

ViewFeatures

0.98

 Мексичка

0.96

aarrggbb

0.94

bewerken

0.92

StructEnd

0.91

InjectAttribute

0.89

 تضيفلها

0.89

expandindo

0.88

 resourceCulture

0.86

Activations Density 0.185%

terms related to various scientific and medical contexts, particularly focusing on faith, taxation, and biological markers

No Comments

No Known Activations