INDEX

Explanations

elements related to medical treatment and dosing information

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

simplification or reduction

np_acts-logits-general · gemini-2.0-flash

simplification and reduction

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

">//

-0.45

NewGuid

-0.44

awaiter

-0.42

AddAttribute

-0.42

 Chwiliwch

-0.40

ram

-0.39

 hostages

-0.38

Traceback

-0.38

iação

-0.38

lee

-0.37

POSITIVE LOGITS

 simplifies

0.96

 simplify

0.92

 simplification

0.91

 fewer

0.89

 reduced

0.89

 Fewer

0.88

不需要

0.88

 simplified

0.87

 simpler

0.87

 simplifying

0.86

Activations Density 0.568%

elements related to medical treatment and dosing information

simplification or reduction

simplification and reduction

No Comments

No Known Activations