INDEX

Explanations

elements related to data structure or programming terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

knapp

-0.54

المكان

-0.54

lip

-0.53

manded

-0.51

AddTagHelper

-0.50

INCREMENT

-0.49

áctenos

-0.49

 Magistrates

-0.48

uncu

-0.48

cidae

-0.47

POSITIVE LOGITS

tagHelperRunner

0.92

ineno

0.70

 utafitiHapana

0.63

 '\\;'

0.61

CloseOperation

0.61

HasForeignKey

0.60

 ویکی‌پدیای

0.59

ſelves

0.59

QMetaType

0.59

 iprot

0.58

Activations Density 0.300%

elements related to data structure or programming terms

No Comments

No Known Activations