INDEX

Explanations

specific terms related to film and television production, commentary, and narrative structure

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

-0.49

ाव

-0.48

dou

-0.46

di

-0.45

Di

-0.45

рый

-0.45

ﾉ

-0.42

 unos

-0.42

phora

-0.42

POSITIVE LOGITS

 ExecuteAsync

0.79

 تانيه

0.77

 ویکی‌پدیای

0.73

 anún

0.71

 समीक्षक

0.71

 defaultstate

0.67

+:+

0.65

awtextra

0.64

ItemBackground

0.63

 otomatig

0.63

Activations Density 1.591%

specific terms related to film and television production, commentary, and narrative structure

No Comments

No Known Activations