INDEX

Explanations

elements indicating a structured or formatted list

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

)++;

-0.52

 CURLOPT

-0.51

putExtra

-0.47

setts

-0.46

-0.44

XmlAccessType

-0.44

nants

-0.41

Personendaten

-0.41

ETIME

-0.41

arote

-0.40

POSITIVE LOGITS

 kasarigan

0.97

 חיצוניים

0.85

Bibliograf

0.79

CrossRef

0.73

 doubtnut

0.71

 purpoſe

0.68

 Leurs

0.68

fortawesome

0.67

contentLoaded

0.67

DoubleQuotes

0.66

Activations Density 0.627%

elements indicating a structured or formatted list

No Comments

No Known Activations