INDEX

Explanations

proper nouns, specifically names of people and places

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

Names, often followed by last names or titles

np_acts-logits-general · gemini-2.0-flash

names of people

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

 betweenstory

-0.64

 surla

-0.57

 externi

-0.57

 Chwiliwch

-0.52

blurRadius

-0.51

exitRule

-0.47

Egl

-0.46

protoimpl

-0.46

 CreateTagHelper

-0.45

CLC

-0.44

POSITIVE LOGITS

Joe

0.71

Bob

0.67

Jim

0.66

Pete

0.65

JOE

0.62

Joe

0.61

Charlie

0.57

JOE

0.57

Bob

0.56

 Pete

0.56

Activations Density 0.310%

proper nouns, specifically names of people and places

Names, often followed by last names or titles

names of people

No Comments

No Known Activations