INDEX

Explanations

conversational phrases and expressions related to hypothetical scenarios

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 surla

-0.46

 برانيه

-0.40

delmi

-0.39

deen

-0.38

rais

-0.38

BibitemShut

-0.38

 TextAlign

-0.36

loyees

-0.36

setcounter

-0.36

 MainAxisSize

-0.35

POSITIVE LOGITS

 AssemblyTitle

0.59

 autorytatywna

0.47

 createState

0.45

Autoritní

0.43

 fapt

0.43

yntaxException

0.42

 eigenlijk

0.42



0.41

 argint

0.41

 plegable

0.40

Activations Density 0.309%

conversational phrases and expressions related to hypothetical scenarios

No Comments

No Known Activations