INDEX

Explanations

terms and phrases related to plain or simple language in formal contexts

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

plain language or error

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

 Normdatei

-0.48

FunctionFlags

-0.47

ValueStyle

-0.44

="@+

-0.40

BeginContext

-0.36

 ffilmiau

-0.36

importanza

-0.36

 inesperado

-0.36

HtmlAttribute

-0.35

+:+

-0.35

POSITIVE LOGITS

Plain

1.59

 plain

1.53

 Plain

1.52

plain

1.48

 plaintext

1.13

PLAIN

1.13

plaintext

1.11

PlainText

1.05

 plainly

1.05

 plains

0.90

Activations Density 0.022%

terms and phrases related to plain or simple language in formal contexts

plain language or error

No Comments

No Known Activations