INDEX

Explanations

phrases related to user preferences and notifications

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

in

-1.13

-1.08

-1.03

and

-1.03

to

-0.98

-0.97

for

-0.96

-0.93

an

-0.92

POSITIVE LOGITS

 myſelf

1.87

Efq

1.82

 feroit

1.81

 auroit

1.80

 itſelf

1.80

 ainfi

1.80

 Monfieur

1.79

 ſeveral

1.74

 Houſe

1.71

 Reſ

1.69

Activations Density 0.105%

phrases related to user preferences and notifications

No Comments

No Known Activations