INDEX

Explanations

instances of the word "when" indicating temporal context in events

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

 ISNI

-0.67

MLLoader

-0.64

τής

-0.63

adaptiveStyles

-0.61

[++

-0.59

iestety

-0.59

 ביותר

-0.58

KommentareTeilen

-0.58

 کاش

-0.57

 Suggest

-0.57

POSITIVE LOGITS

When

1.76

 When

1.72

WHEN

1.49

when

1.45

 WHEN

1.43

 when

1.34

Когда

1.30

Quando

1.29

Cuando

1.27

 Quando

1.25

Activations Density 0.073%

instances of the word "when" indicating temporal context in events

No Comments

No Known Activations