INDEX

Explanations

terms related to data handling, particularly errors or conditions that specify constraints and limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

URLException

-0.84

 Wikimedijinoj

-0.78

MetaObject

-0.75

 surla

-0.72

☸

-0.70

OGND

-0.70

aarrggbb

-0.69

StoryboardSegue

-0.68

UnsafeEnabled

-0.67

 Mercier

-0.66

POSITIVE LOGITS

setDo

0.69

Use

0.58

Non

0.58

 need

0.56

 Need

0.56

non

0.54

<bos>

0.53

非

0.53

Non

0.53

要

0.52

Activations Density 0.338%

terms related to data handling, particularly errors or conditions that specify constraints and limitations

No Comments

No Known Activations