INDEX

Explanations

numerical data points or timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 sebaliknya

-0.51

 corresponding

-0.48

Tô

-0.48

 Tetrahedron

-0.47

 ché

-0.47

 deme

-0.46

 Frente

-0.46

Cfr

-0.46

itinéraire

-0.45

 effe

-0.45

POSITIVE LOGITS

 betweenstory

0.73

HasAnnotation

0.69

 propOrder

0.69

 tartalomajánló

0.68

OGND

0.62

 mergeFrom

0.62

parsedMessage

0.60

AddTagHelper

0.60

addGap

0.59

̍t

0.58

Activations Density 0.562%

numerical data points or timestamps

No Comments

No Known Activations