INDEX

Explanations

elements related to themes in television shows, particularly discussions about character relationships and story arcs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 متعلقه

-0.80

AccessorTable

-0.68

ništvo

-0.68

 referenties

-0.67

RenderAtEndOf

-0.64

esModule

-0.62

LookAnd

-0.60

thenes

-0.59

useState

-0.57

migrationBuilder

-0.56

POSITIVE LOGITS

 episode

1.34

 season

1.10

episode

1.10

Episode

1.08

 episodes

1.07

 Season

1.03

 Episode

1.02

Season

0.93

season

0.93

episodes

0.85

Activations Density 0.219%

elements related to themes in television shows, particularly discussions about character relationships and story arcs

No Comments

No Known Activations