INDEX

Explanations

expressions indicating skepticism or doubt regarding information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

TagMode

-0.56

BuilderFactory

-0.55

ånga

-0.54

ipelago

-0.53

 ComVisible

-0.52

 KeyError

-0.50

getRuntime

-0.49

UnusedPrivate

-0.48

XMLHttpRequest

-0.48

)‏

-0.48

POSITIVE LOGITS

THING

1.04

 THING

0.95

 thing

0.92

 things

0.92

thing

0.90

 everything

0.90

everything

0.87

 stuff

0.86

 Thing

0.86

anything

0.84

Activations Density 0.387%

expressions indicating skepticism or doubt regarding information

No Comments

No Known Activations