INDEX

Explanations

instances of the word "all" across various contexts

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

all followed by a noun

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

彻

-0.51

__((

-0.45

protoc

-0.45

ättä

-0.44

CppMethod

-0.43

⟬

-0.43

徹

-0.43

 chart

-0.42

MessageOf

-0.41

Carta

-0.41

POSITIVE LOGITS

abstractmethod

0.56

 '\\;'

0.49

تفصیلات

0.45

ALWAYS

0.40

 wszyst

0.40

 Every

0.39

keyColumn

0.38

 Semua

0.38

 Todas

0.38

Every

0.38

Activations Density 0.043%

instances of the word "all" across various contexts

all followed by a noun

No Comments

No Known Activations

instances of the word "all" across various contexts

all followed by a noun

No Comments

No Known Activations