INDEX

Explanations

phrases and actions related to decision-making and determining outcomes

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

Referanser

-0.65

withstanding

-0.63

expandindo

-0.57

ikum

-0.56

 Wikimedijinoj

-0.55

soever

-0.55

とも

-0.54

Abitanti

-0.53

 Reverso

-0.53

Дереккөздер

-0.53

POSITIVE LOGITS

 which

3.12

which

2.62

 Which

2.62

Which

2.58

 WHICH

2.58

who

1.76

 quale

1.75

 whom

1.70

 laquelle

1.66

 quais

1.63

Activations Density 0.646%

phrases and actions related to decision-making and determining outcomes

No Comments

No Known Activations