INDEX

Explanations

words and phrases related to actions and parameters in a software or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

__':

-0.90

rungsseite

-0.84

 NSCoder

-0.81

ⓧ

-0.79

ViewFeatures

-0.78

 CreateTagHelper

-0.76

 autorytatywna

-0.71

 FetchType

-0.70

SourceChecksum

-0.69

expandindo

-0.69

POSITIVE LOGITS

 section

2.30

 sections

1.58

section

1.54

tab

1.47

 category

1.45

 subsection

1.44

 Section

1.40

 sección

1.35

 sezione

1.33

 SECTION

1.29

Activations Density 0.701%

words and phrases related to actions and parameters in a software or technical context

No Comments

No Known Activations