INDEX

Explanations

references to document formatting properties, specifically related to dimensions

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

 kasarigan

-0.84

 nakalista

-0.79

ParallelGroup

-0.73

ScopeManager

-0.73

ukone

-0.73

]$}

-0.69

 StringTokenizer

-0.68

]));

-0.66

bootstrapcdn

-0.66

IsContent

-0.66

POSITIVE LOGITS

textwidth

1.47

 rédaction

0.49

 становника

0.48

 arcos

0.47

 României

0.46

 lengte

0.46

atimes

0.45

columnwidth

0.45

̀

0.45

 emporter

0.45

Activations Density 0.030%

references to document formatting properties, specifically related to dimensions

No Comments

No Known Activations