INDEX

Explanations

the repetitive usage of the word "there" in various contexts

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

there followed by existence verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 queſta

-0.66

 CURIAM

-0.65

:✨

-0.64

UserScript

-0.63

󠁿

-0.61

parsedMessage

-0.61



-0.61

 TextInputType

-0.60

 GenerationType

-0.60

征詢我

-0.59

POSITIVE LOGITS

 there

1.13

there

0.98

There

0.91

 There

0.83

 THERE

0.80

THERE

0.74

no

0.61

it

0.60

 theres

0.59

 they

0.57

Activations Density 0.076%

the repetitive usage of the word "there" in various contexts

there followed by existence verbs

No Comments

No Known Activations