INDEX

Explanations

numeric data or specific formatting related to versions or codes

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

SequentialGroup

-1.02

 للاسماء

-0.98

 purpoſe

-0.94

ResponseWriter

-0.92

BeginInit

-0.90

 GenerationType

-0.89

EndGlobalSection

-0.88

reportWebVitals

-0.87

 myſelf

-0.86

 CreateTagHelper

-0.85

POSITIVE LOGITS

0.45

0.41

 humaines

0.40

lüssel

0.39

</strong>

0.38

 wichtigsten

0.38

 nhật

0.38

San

0.37

quot

0.37

 строе

0.37

Activations Density 0.358%

numeric data or specific formatting related to versions or codes

No Comments

No Known Activations