INDEX

Explanations

positive sentiments and expressions of approval

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

preceding positive adjectives

np_acts-logits-general · gemini-2.0-flash

positive evaluation

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

ScopeManager

-0.49

SQLException

-0.49

 injuries

-0.47

 toán

-0.43

 Infórmanos

-0.43

瘩

-0.43

 związ

-0.43

 vragen

-0.42

 GenerationType

-0.42

RTE

-0.41

POSITIVE LOGITS

 Normdatei

0.69

mapStateToProps

0.64

 насељу

0.63

 dzięki

0.62

 good

0.62

WithIOException

0.58

 advantages

0.58

 vantaggi

0.58

 advantage

0.58

httphttps

0.58

Activations Density 0.424%

positive sentiments and expressions of approval

preceding positive adjectives

positive evaluation

No Comments

No Known Activations