INDEX

Explanations

ellipsis or interruptions in text

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

Followed by "Read" or URLs

np_acts-logits-general · gemini-2.0-flash

tokens starting with punctuation or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

in

-0.57

and

-0.54

-0.52

-0.51

-0.50

for

-0.50

-0.49

on

-0.49

POSITIVE LOGITS

 ModelExpression

1.18

MLLoader

0.94

 propOrder

0.93

".

0.92

Tembelea

0.91

 Roskov

0.89

 itſelf

0.89

 esternos

0.88

IUrlHelper

0.88

SourceChecksum

0.87

Activations Density 0.077%

ellipsis or interruptions in text

Followed by "Read" or URLs

tokens starting with punctuation or symbols

No Comments

No Known Activations