INDEX

Explanations

references to people and relationships in a narrative context

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

Followed by helping verbs

np_acts-logits-general · gemini-2.0-flash

"mind" followed by "USA"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Additionally

-0.60

 Additionally

-0.57

Moreover

-0.57

:!

-0.54

 usuf

-0.54

findpost

-0.54

apura

-0.52

RenderAtEndOf

-0.52

:✨

-0.52

 Notably

-0.52

POSITIVE LOGITS

 yeah

0.78

Remover

0.75

oh

0.72

 Yeah

0.71

<bos>

0.65

 gonna

0.65

 tryna

0.64

Cause

0.64

Ведь

0.64

Oh

0.63

Activations Density 0.124%

references to people and relationships in a narrative context

Followed by helping verbs

"mind" followed by "USA"

No Comments

No Known Activations