INDEX

Explanations

phrases emphasizing clarification and notes about important information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

RefNanny

-0.64

ImageField

-0.59

راث

-0.52

GeneratedCode

-0.50

splitlines

-0.48

령

-0.47

basicConfig

-0.46

 McGuire

-0.45

rshire

-0.44

quité

-0.44

POSITIVE LOGITS

 note

0.92

 reminder

0.82

 Note

0.76

brigens

0.75

 remind

0.73

 NOTE

0.73

note

0.72

Reminder

0.71

 Reminder

0.69

Note

0.69

Activations Density 0.266%

phrases emphasizing clarification and notes about important information

No Comments

No Known Activations