INDEX

Explanations

statements that suggest underlying connections or causal relationships in research or findings

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

"Suggesting that" followed by a clause

np_acts-logits-general · gemini-2.0-flash

suggesting an inference

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ttemberg

-0.47

:✨

-0.44

 stället

-0.41

RegistryLite

-0.41

 maș

-0.40

 igång

-0.37

IsUnicode

-0.37

 rând

-0.37

UrlResolution

-0.37

Portail

-0.36

POSITIVE LOGITS

 didalam

0.57

.*")]

0.54

 coloured

0.54

ConstraintMaker

0.54

 CommonModule

0.53

 loosing

0.53

 COLOUR

0.52

 colour

0.52

/***/

0.52

허

0.51

Activations Density 1.280%

statements that suggest underlying connections or causal relationships in research or findings

"Suggesting that" followed by a clause

suggesting an inference

No Comments

No Known Activations