INDEX

Explanations

actions and attributes related to taking responsibility

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

preceding pronouns

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

GenerationType

-0.54

 Оно

-0.48

彼が

-0.46

它的

-0.44

是一個

-0.43

ellum

-0.43

的他

-0.42

 оно

-0.41

是個

-0.41

它

-0.40

POSITIVE LOGITS

 themselves

2.28

 their

1.98

themselves

1.94

their

1.78

Their

1.77

 Their

1.72

他們的

1.57

他们的

1.51

 ihre

1.49

 leurs

1.47

Activations Density 2.101%

actions and attributes related to taking responsibility

preceding pronouns

No Comments

No Known Activations