INDEX

Explanations

references to military or governmental structures and operations

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

</b>

-0.88

↵

-0.81

</strong>

-0.75

########.

-0.70

-0.67

ViewFeatures

-0.65

 everybody

-0.65

-0.64

"}

-0.64

-0.63

POSITIVE LOGITS

 Alamy

0.67

DockStyle

0.64

WithIOException

0.64

 muualla

0.60

 varandra

0.59

 relâche

0.56

 vänner

0.56

 समीक्षाओं

0.56

 Inflate

0.56

Ārējās

0.55

Activations Density 0.003%

references to military or governmental structures and operations

No Comments

No Known Activations