INDEX

Explanations

the use of the word "into" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 âgées

-0.75

GRAPH

-0.72

 Balboa

-0.72

 africains

-0.70

 Calvo

-0.69

 peint

-0.69

AAS

-0.68

PAH

-0.67

Weh

-0.67

 Mesozoic

-0.66

POSITIVE LOGITS

 INTO

1.71

 Into

1.66

Into

1.61

 into

1.54

INTO

1.40

into

1.20

 onto

0.96

")){

0.88

"])){

0.86

*</

0.85

Activations Density 0.117%

the use of the word "into" in various contexts

No Comments

No Known Activations