INDEX

Explanations

variable and function definitions along with related programming constructs

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

-1.12

-1.00

in

-0.95

-0.94

the

-0.94

-0.90

“

-0.88

for

-0.87

‘

-0.83

-0.82

POSITIVE LOGITS

 Reſ

1.26

 Monfieur

1.25

ſelves

1.24

 myſelf

1.24

ſelf

1.24

 ſche

1.23

+#+#

1.22

 pleaſure

1.22

 Jefus

1.21

 itſelf

1.18

Activations Density 0.416%

variable and function definitions along with related programming constructs

No Comments

No Known Activations