INDEX

Explanations

phrases indicating consequences or results, typically starting with "leads to" or "led to".

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @danielepoterti

phrases indicating causation or outcomes related to actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

utilisons

-0.50

 virtuel

-0.44

 Utilizamos

-0.42

belea

-0.42

ruik

-0.41

 Chriftian

-0.39

contest

-0.38

 exercício

-0.38

cag

-0.37

ſelf

-0.37

POSITIVE LOGITS

 leads

1.13

leads

1.03

 Leads

1.03

Leads

0.97

led

0.96

 leading

0.95

 führt

0.94

 lead

0.92

leading

0.90

 führen

0.87

Activations Density 0.244%

phrases indicating consequences or results, typically starting with "leads to" or "led to".

phrases indicating causation or outcomes related to actions

No Comments

No Known Activations