INDEX

Explanations

details about fictional characters and their roles in films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ScopeManager

-0.63

+#+

-0.58

AndEndTag

-0.56

 يتيمه

-0.52

 OMIT

-0.51

 Erişim

-0.51

 handleMessage

-0.51

 ModelExpression

-0.51

 Pristupljeno

-0.49

########.

-0.47

POSITIVE LOGITS

 müßte

0.64

 wester

0.62

탤

0.61

MGM

0.61

 vedette

0.61

ⓧ

0.60

 contribué

0.60

 melodrama

0.58

 wußte

0.58

 erad

0.57

Activations Density 0.354%

details about fictional characters and their roles in films

No Comments

No Known Activations