INDEX

Explanations

references to personal growth and self-discovery

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

Followed by a personal pronoun

np_acts-logits-general · gemini-2.0-flash

i and me

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

")->

-0.68

いきましょう

-0.63

ſelves

-0.63

raszamy

-0.63

помним

-0.63

きましょう

-0.61

ſelf

-0.60

">:

-0.60

CloseOperation

-0.57

みましょう

-0.56

POSITIVE LOGITS

my

3.65

 myself

2.70

my

2.58

 mijn

2.55

 meiner

2.42

 meines

2.41

 моих

2.36

 моего

2.33

我的

2.32

 meus

2.29

Activations Density 4.114%

references to personal growth and self-discovery

Followed by a personal pronoun

i and me

No Comments

No Known Activations