INDEX

Explanations

words related to events and notable acknowledgments

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

followed by a preposition

np_acts-logits-general · gemini-2.0-flash

past tense participles introducing facts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

WriteTagHelper

-0.76

NOPQRST

-0.69

ThroughAttribute

-0.64

NewUrlParser

-0.62

impulan

-0.60

 وأن

-0.59

 invokingState

-0.59

Hauptartikel

-0.58

WithIOException

-0.57

 متعلقه

-0.57

POSITIVE LOGITS

的是

0.62

are

0.51

readLine

0.48

is

0.45

 ostavi

0.43

 navbar

0.43

standen

0.42

batore

0.41

 initComponents

0.41

pi

0.41

Activations Density 0.360%

words related to events and notable acknowledgments

followed by a preposition

past tense participles introducing facts

No Comments

No Known Activations