INDEX

Explanations

structural elements of HTML or XML documents

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

 myſelf

-0.97

 itſelf

-0.95

Efq

-0.83

 poffible

-0.82

 Majefty

-0.80

ſelves

-0.78

ſelf

-0.75

 purpoſe

-0.75

 doubtnut

-0.75

+:+

-0.75

POSITIVE LOGITS

numerusform

0.54

rel

0.47

0.46

ValueGenerated

0.45

0.43

cy

0.42

fer

0.41

 cây

0.40

centerTitle

0.39

Activations Density 0.147%

structural elements of HTML or XML documents

No Comments

No Known Activations