INDEX

Explanations

phrases indicating medical conditions and treatments

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

UnusedPrivate

-0.51

ImageContext

-0.49

MigrationBuilder

-0.48

 nakalista

-0.46

כש

-0.46

いかがでしたか

-0.46

 znamen

-0.46

書館

-0.46

 wikipagina

-0.45

antaranya

-0.45

POSITIVE LOGITS

 disambiguazione

0.41

tagHelperRunner

0.41

kannt

0.35

 lenker

0.35

stair

0.34

tät

0.34

 CYTHON

0.32

 يتيمه

0.32

OGND

0.32

OCCURRED

0.32

Activations Density 0.035%

phrases indicating medical conditions and treatments

No Comments

No Known Activations