INDEX

Explanations

references to upper and lower anatomical regions, particularly in medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

jooq

-0.70

#+#

-0.62

исленность

-0.60

PreferredItem

-0.59

interopRequire

-0.58

XDECREF

-0.56

GEBURTSDATUM

-0.54

IndentedString

-0.53

 utafitiHapana

-0.52

UnusedPrivate

-0.52

POSITIVE LOGITS

most

0.94

MOST

0.75

 bound

0.70

case

0.59

 extremity

0.59

 reaches

0.59

cased

0.58

Bound

0.58

 half

0.58

 limit

0.57

Activations Density 0.309%

references to upper and lower anatomical regions, particularly in medical contexts

No Comments

No Known Activations