INDEX

Explanations

terms related to academic achievements and contributions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 superiori

-0.52

 officiers

-0.46

 akibat

-0.45

dataTables

-0.44

 eftersom

-0.43

зумі

-0.43

Spoljašnje

-0.42

 keberadaan

-0.42

 precedenti

-0.41

 dată

-0.41

POSITIVE LOGITS

 many

0.97

 several

0.90

 both

0.90

 numerous

0.85

 only

0.83

 saites

0.82

 dozens

0.81

several

0.81

 sowohl

0.80

 både

0.79

Activations Density 0.513%

terms related to academic achievements and contributions

No Comments

No Known Activations