INDEX

Explanations

phrases indicating conclusions or results

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

preceding "up" or "in" after forms of "end"

np_acts-logits-general · gemini-2.0-flash

ended up

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

LEncoder

-0.71

 leaſt

-0.68

ContentAsync

-0.66

énario

-0.65

Personensuche

-0.64

atorics

-0.62

 IBOutlet

-0.61

 starlight

-0.60

IntoConstraints

-0.59

 pleaſure

-0.59

POSITIVE LOGITS

 with

0.64

DrawerToggle

0.58

up

0.56

 like

0.56

setVerticalGroup

0.55

minar

0.53

 right

0.52

on

0.52

zys

0.51

 sooner

0.50

Activations Density 0.100%

phrases indicating conclusions or results

preceding "up" or "in" after forms of "end"

ended up

No Comments

No Known Activations