INDEX

Explanations

formatting and rounding instructions related to numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 mutagen

-0.63

 المعيارى

-0.59

ExecuteReader

-0.57

 متعلقه

-0.57

 lenker

-0.56

 سكانية

-0.56

UVWXYZ

-0.56

assium

-0.55

 onFailure

-0.55

 EClass

-0.55

POSITIVE LOGITS

iomanip

0.63

Cyfeiriadau

0.61

 decimals

0.56

Accuracy

0.54

 TextAlign

0.54

 accuracy

0.53

plained

0.53

 decimal

0.52

两位

0.52

 digits

0.51

Activations Density 0.150%

formatting and rounding instructions related to numerical values

No Comments

No Known Activations