INDEX

Explanations

terms related to drug usage and its effects

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

Followed by infinitive "to"

np_acts-logits-general · gemini-2.0-flash

purpose requiring action

np_acts-logits-general · gemini-2.5-flash-lite

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

:✨

-0.94

 insuffisamment

-0.74

PerformLayout

-0.72



-0.72

RegressionTest

-0.71

RunWith

-0.69

lapsingToolbar

-0.67

parsedMessage

-0.67

цездатний

-0.67

toplas

-0.66

POSITIVE LOGITS

 чтобы

1.90

 כדי

1.80

 để

1.80

to

1.74

เพื่อ

1.68

 щоб

1.62

 upang

1.56

 afin

1.46

 affinch

1.36

 чтоб

1.32

Activations Density 3.299%

terms related to drug usage and its effects

Followed by infinitive "to"

purpose requiring action

No Comments

No Known Activations