INDEX

Explanations

expressions related to criticism or recommendations regarding people's behavior and social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

">//

-0.65

koli

-0.55

מעט

-0.47

 föruts

-0.47

>//

-0.45

PropertyGroup

-0.45

openSession

-0.44

 consentimento

-0.44

ViewImports

-0.43

POSITIVE LOGITS

 stop

1.26

 Stop

1.14

 shut

1.11

Stop

1.10

 STOP

1.08

stop

1.06

 Shut

1.06

Shut

1.01

 SHUT

1.01

shut

1.01

Activations Density 0.243%

expressions related to criticism or recommendations regarding people's behavior and social issues

No Comments

No Known Activations