INDEX

Explanations

plural nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 raiſ

-0.97

 chofe

-0.97

 poffible

-0.92

 myſelf

-0.89

 deſt

-0.89

 caufe

-0.87

 becauſe

-0.85

 doubtnut

-0.85

 themſelves

-0.85

 subsidi

-0.85

POSITIVE LOGITS

1.62

1.11

󠁿

0.83

’,

0.83

ｓ

0.76

’.

0.76

檚

0.74

’)

0.74

ンの

0.74

€™

0.73

Activations Density 0.191%

plural nouns

No Comments

No Known Activations