INDEX

Explanations

occurrences of terms or phrases related to terms and their definitions in a formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Frey

-0.70

 Schweitzer

-0.67

\]

-0.65

 flott

-0.63

 pasti

-0.62

 Esco

-0.62

ضير

-0.61

enetrable

-0.61

 adipo

-0.61

 Frey

-0.61

POSITIVE LOGITS

 TERM

1.41

 Term

1.38

 Terms

1.35

 terms

1.35

terms

1.24

Terms

1.23

 TERMS

1.22

 term

1.20

Term

1.16

TERM

1.12

Activations Density 0.090%

occurrences of terms or phrases related to terms and their definitions in a formal context

No Comments

No Known Activations