INDEX

Explanations

phrases indicating opposition or critiques of government actions and policies

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

Statements of opinion or criticism

np_acts-logits-general · gemini-2.0-flash

shouldn't or blaming

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

 forklar

-0.58

meist

-0.57

 exacta

-0.54

ناية

-0.54

BagConstraints

-0.53

 déterminé

-0.52

 exacte

-0.51

 bedingt

-0.50

 Occasionally

-0.50

 contado

-0.49

POSITIVE LOGITS

 shouldn

0.80

 blaming

0.76

Shouldn

0.74

 surely

0.74

 Shouldn

0.73

 banning

0.73

 seharusnya

0.72

 shame

0.71

 unless

0.71

 inaction

0.71

Activations Density 0.439%

phrases indicating opposition or critiques of government actions and policies

Statements of opinion or criticism

shouldn't or blaming

No Comments

No Known Activations