INDEX

Explanations

terms related to neural network architecture and functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

saraba

-0.49

 transition

-0.47

ktes

-0.46

oob

-0.46

oem

-0.45

 Transition

-0.45

 demografica

-0.45

hla

-0.44

lot

-0.43

POSITIVE LOGITS

évaluateur

0.72

 يتيمه

0.70

istoitu

0.68

 вікі

0.64

IGraphics

0.63

TintMode

0.62

GenerationType

0.62

 MainAxisSize

0.62

WireFormat

0.61

WritableDatabase

0.61

Activations Density 0.261%

terms related to neural network architecture and functionality

No Comments

No Known Activations