INDEX

Explanations

references to notable individuals or institutions, particularly those related to halls of fame

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

bê

-0.84

 Devine

-0.77

sê

-0.77

>>>>>

-0.74

 Bisch

-0.74

 Stokes

-0.73

 Agrico

-0.73

 виправивши

-0.73

<tbody>

-0.71

oglobulin

-0.71

POSITIVE LOGITS

 hall

1.57

 Hall

1.55

 halls

1.55

 HALL

1.51

 Halls

1.49

hall

1.37

Hall

1.30

HALL

1.30

 hallway

0.98

 Haller

0.98

Activations Density 0.009%

references to notable individuals or institutions, particularly those related to halls of fame

No Comments

No Known Activations