INDEX

Explanations

ethical considerations and comparisons related to practices and behaviors

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

"as" followed by "possible"

np_acts-logits-general · gemini-2.0-flash

as possible

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

ParallelGroup

-0.65

awtextra

-0.63

enumi

-0.63

InjectAttribute

-0.60

AccessorTable

-0.58

UnknownFields

-0.58

Enllaços

-0.55

 autorytatywna

-0.55

 Процитовано

-0.54

jstor

-0.54

POSITIVE LOGITS

 possible

4.18

possible

3.65

 Possible

3.39

Possible

3.32

 POSSIBLE

3.20

 posible

3.10

 possibile

2.95

 posibles

2.88

 possível

2.85

 possibles

2.83

Activations Density 0.717%

ethical considerations and comparisons related to practices and behaviors

"as" followed by "possible"

as possible

No Comments

No Known Activations