INDEX

Explanations

references to frequencies and intervals of actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 daily

-0.90

 <<<<<<<<<<<<<<

-0.84

 للمعارف

-0.84

 DAILY

-0.79

DAILY

-0.78

daily

-0.77

 Daily

-0.76

Daily

-0.74

 günlük

-0.70

endphp

-0.70

POSITIVE LOGITS

 every

1.44

every

1.29

Every

1.15

 Every

1.11

 intervals

1.01

 interval

0.97

 каж

0.90

 ogni

0.87

interval

0.83

 INTERVAL

0.80

Activations Density 0.173%

references to frequencies and intervals of actions or events

No Comments

No Known Activations