INDEX

Explanations

specific numerical data or identifiers within texts, particularly in relation to statistics or references to items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 незавершена

-0.95

出版年

-0.92

WebElementEntity

-0.89

شهاد

-0.87

tagHelperRunner

-0.86

 ddelweddau

-0.86

énario

-0.84

IntoConstraints

-0.83

 JpaRepository

-0.79

 AppBundle

-0.78

POSITIVE LOGITS

↵↵

0.65

↵

0.58

Shea

0.51

<eos>

0.50

itm

0.47

</blockquote>

0.46

 Pute

0.44

<sup>

0.43

<bos>

0.43

Activations Density 0.086%

specific numerical data or identifiers within texts, particularly in relation to statistics or references to items

No Comments

No Known Activations