INDEX

Explanations

conjunctions and transition words that indicate causality or consequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 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

 whoſe

-0.59

 aeruginosa

-0.59

gucig

-0.57

evaluator

-0.56

JsonInclude

-0.55

 evaluator

-0.54

 verſ

-0.54

 Theſe

-0.54

 weevil

-0.54

mahan

-0.54

POSITIVE LOGITS

 therefore

0.61

Therefore

0.55

 thereby

0.54

therefore

0.54

 Therefore

0.54

Thus

0.53

 Thus

0.52

 Quindi

0.50

 thus

0.50

 accordingly

0.48

Activations Density 0.272%

conjunctions and transition words that indicate causality or consequence

No Comments

No Known Activations