INDEX

Explanations

technical terminology related to medical procedures and measurements

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

"in" followed by a preposition or article

np_acts-logits-general · gemini-2.0-flash

in relation to

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 AssemblyCompany

-0.73

 lenker

-0.69

Autoritní

-0.64

 CreateTagHelper

-0.61

migrationBuilder

-0.56

LabelTagHelper

-0.55

 Mitteln

-0.54

RTDA

-0.51

RenderAtEndOf

-0.49

 calendriers

-0.49

POSITIVE LOGITS

iuo

0.64

ceased

0.60

tvguidetime

0.57

 contact

0.57

ert

0.55

 laboratory

0.53

runners

0.52

 combination

0.50

ьа

0.50

 Situ

0.49

Activations Density 0.707%

technical terminology related to medical procedures and measurements

"in" followed by a preposition or article

in relation to

No Comments

No Known Activations