INDEX

Explanations

references to films, particularly their titles, genres, directors, and production details

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

OGND

-0.78

 дописавши

-0.65

udahkan

-0.62

 RSSSF

-0.60

 jsPsych

-0.58

новништво

-0.58

oforms

-0.58

GEBURTSDATUM

-0.57

رامج

-0.56

GOTREF

-0.56

POSITIVE LOGITS

 depicts

0.83

 about

0.82

 depicting

0.80

 featuring

0.77

 inspired

0.73

 based

0.73

 portrays

0.72

 starring

0.71

 revolves

0.71

 explores

0.71

Activations Density 0.274%

references to films, particularly their titles, genres, directors, and production details

No Comments

No Known Activations