INDEX

Explanations

words related to sensitivity, justification, and legal terms

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

ending in "ti" or "justi"

np_acts-logits-general · gemini-2.0-flash

titration, sensitivity, justification

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

parsedMessage

-0.82

 AssemblyTitle

-0.74

نه

-0.60

Parcelize

-0.59

UserScript

-0.59

kań

-0.57

WaitGroup

-0.57

 الدولى

-0.54

ческой

-0.52

TestingModule

-0.52

POSITIVE LOGITS

tal

0.53

tt

0.52

tallet

0.50

 ISNI

0.50

ton

0.50

ts

0.48

readyState

0.45

 recientes

0.45

orari

0.44

tsk

0.43

Activations Density 0.227%

words related to sensitivity, justification, and legal terms

ending in "ti" or "justi"

titration, sensitivity, justification

No Comments

No Known Activations