INDEX

Explanations

references to movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 invokingState

-1.12

 kasarigan

-1.03

principalColumn

-0.99

 कृपया

-0.98

Portail

-0.95

prefixer

-0.95

AxisAlignment

-0.92

 okuyayım

-0.92

 '\\;'

-0.91

IContainer

-0.89

POSITIVE LOGITS

 movies

1.47

 movie

1.43

 Movie

1.23

 Movies

1.19

Movie

1.19

Movies

1.17

 MOVIE

1.14

movies

1.10

movie

1.03

MOVIE

0.87

Activations Density 0.081%

references to movies

No Comments

No Known Activations