INDEX

Explanations

terms related to neurotransmitters and the specific parameters of experimental variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

GEBURTSDATUM

-0.41

 pleaf

-0.39

Portály

-0.34

AutoScaleMode

-0.33

 المرجع

-0.31

 ſon

-0.30

WaitGroup

-0.30

RTEX

-0.29

ละเอียด

-0.29

 जाता

-0.28

POSITIVE LOGITS

expandindo

0.63

ArrowToggle

0.60

تقاوى

0.57

 ligiloj

0.57

]")]

0.56

AddTagHelper

0.55

 AssemblyTitle

0.54

клопе

0.51

 linkovi

0.51

EndGlobalSection

0.50

Activations Density 0.085%

terms related to neurotransmitters and the specific parameters of experimental variables

No Comments

No Known Activations