INDEX

Explanations

phrases related to forward-looking statements and projections

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

"Forward" or direction-related words

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

complexContent

-0.64

 Roskov

-0.63

oredCriteria

-0.59

cinogenicity

-0.54

Билгалдахарш

-0.53

ьаж

-0.52

MENAFN

-0.52

 torebka

-0.48

 ConstraintSet

-0.48

Життєпис

-0.47

POSITIVE LOGITS

 Forward

0.66

Forward

0.63

 forward

0.63

backward

0.55

forward

0.54

 FORWARD

0.53

FORWARD

0.52

ward

0.48

 forwards

0.48

 ward

0.47

Activations Density 0.115%

phrases related to forward-looking statements and projections

"Forward" or direction-related words

No Comments

No Known Activations