INDEX

Explanations

markers or indicators of document structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

tvguidetime

-0.76

PreferredItem

-0.72

̍t

-0.68

ChildScrollView

-0.67

 صوتيه

-0.66

estars

-0.65

VideoCapture

-0.65

êques

-0.63

المكان

-0.62

onOptions

-0.62

POSITIVE LOGITS

 rowspan

0.58

 colspan

0.57

<th>

0.48

<tr>

0.47

ná

0.47

Seg

0.45

го

0.45

comp

0.45

mär

0.44

ResId

0.43

Activations Density 0.043%

markers or indicators of document structure

No Comments

No Known Activations