INDEX

Explanations

phrases indicating suggestions or recommendations

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

related content links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.52

barung

-0.45

defineProperty

-0.44

 chiaramente

-0.42

stätte

-0.42

Unnamed

-0.42

 PROVISIONS

-0.41

beforeEach

-0.41

protoc

-0.41

POSITIVE LOGITS

 Related

1.17

 related

1.14

Related

1.12

related

1.05

Also

0.93

 also

0.91

 Also

0.90

also

0.89

 nakalista

0.79

similar

0.76

Activations Density 0.125%

phrases indicating suggestions or recommendations

Related articles/content

related content links

No Comments

No Known Activations