INDEX

Explanations

statements that express uncertainty or inquiries about possible errors or glitches

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

Uncertainty, possibility, or guessing

np_acts-logits-general · gemini-2.0-flash

s

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 praticamente

-0.65

几乎

-0.59

 prácticamente

-0.59

幾乎

-0.59

Almost

-0.59

 Almost

-0.58

 virtually

-0.56

מעט

-0.55

 sembla

-0.54

 practically

-0.53

POSITIVE LOGITS

GEBURTSDATUM

1.15

 somehow

1.09

 something

0.96

 maybe

0.93

 somewhere

0.92

something

0.91

 perhaps

0.91

somewhere

0.91

Something

0.90

UnusedPrivate

0.86

Activations Density 0.805%

statements that express uncertainty or inquiries about possible errors or glitches

Uncertainty, possibility, or guessing

s

No Comments

No Known Activations