INDEX

Explanations

numerical data or values in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

WithFormat

-0.78

tø

-0.75

 Sabre

-0.72

UGG

-0.71

 Obre

-0.71

 Kasper

-0.70

рас

-0.70

 Maren

-0.70

aderos

-0.70

 egiten

-0.69

POSITIVE LOGITS

1.47

XI

0.87

१

0.70

১

0.70

 Hend

0.67

eleven

0.67

 Eleventh

0.66

jazdu

0.66

１

0.65

 Eleven

0.65

Activations Density 0.773%

numerical data or values in a structured format

No Comments

No Known Activations