INDEX

Explanations

information related to printed outputs and their formatting in documents

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

something is wrong

np_acts-logits-general · gemini-2.0-flash

incorrect or unexpected results

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

MigrationBuilder

-0.61

changer

-0.51

idiary

-0.46

 customizable

-0.44

 Customizable

-0.44

 ComVisible

-0.44

Alike

-0.43

 nâng

-0.42

umet

-0.42

Prob

-0.41

POSITIVE LOGITS

 prematurely

0.82

 improperly

0.75

 incorrectly

0.75

 spurious

0.74

 wrongly

0.73

 unduly

0.72

 weirdly

0.72

 incomplete

0.71

 inappropri

0.70

 premature

0.70

Activations Density 0.629%

information related to printed outputs and their formatting in documents

something is wrong

incorrect or unexpected results

No Comments

No Known Activations