INDEX

Explanations

patterns related to formatting or structural elements in text

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

symbols, asterisks, or specific tokens

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

CloseOperation

-0.52

enumii

-0.52

Enllaços

-0.48

󠁢

-0.47

 rhestr

-0.44

Pgina

-0.43

AnchorTagHelper

-0.43

 dormitórios

-0.42

 CreateTagHelper

-0.41

 discorso

-0.41

POSITIVE LOGITS

0.55

0.49

########.

0.48

0.47

0.46

 ✭✭

0.45

Activations Density 0.048%

patterns related to formatting or structural elements in text

symbols, asterisks, or specific tokens

No Comments

No Known Activations