INDEX

Explanations

occurrences of the letter "m"

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

Contractions with "I'm"

np_acts-logits-general · gemini-2.0-flash

i'm verb

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

 AssemblyCompany

-0.77

 CascadeType

-0.75

TagMode

-0.72

 صوتيه

-0.71

Autoritní

-0.69

transQ

-0.68

 informée

-0.68

ロウィン

-0.68

 EconPapers

-0.68

/**

-0.66

POSITIVE LOGITS

ll

0.64

re

0.57

нибудь

0.41

 theyre

0.41

RE

0.37

ill

0.37

figure

0.34

le

0.32

 figure

0.32

リ

0.31

Activations Density 0.119%

occurrences of the letter "m"

Contractions with "I'm"

i'm verb

No Comments

No Known Activations