INDEX

Explanations

references to awards and accolades related to films

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

 aired

-0.61

 Calab

-0.61

 sitcom

-0.59

出版年

-0.58

Xna

-0.56

AGRAM

-0.55

 irradiation

-0.55

 griff

-0.54

choon

-0.54

illot

-0.54

POSITIVE LOGITS

 <=",

0.67

 kaynağından

0.64

BeginContext

0.62

 propOrder

0.61

AutoresizingMask

0.57

 BrowserModule

0.54

AccessorTable

0.54

∬

0.53

 Fass

0.52

 Leto

0.50

Activations Density 0.171%

references to awards and accolades related to films

No Comments

No Known Activations