INDEX

Explanations

technical jargon related to software or systems operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ylon

-0.50

芽

-0.50

tidig

-0.49

metri

-0.49

:✨

-0.49

ூர்

-0.48

احب

-0.48

沿革

-0.48

pektor

-0.48

unkel

-0.47

POSITIVE LOGITS

scalatest

0.71

ValueGeneration

0.69

 always

0.66

Xna

0.59

SourceChecksum

0.58

 veliko

0.57

migrationBuilder

0.57

 Arhi

0.57

providedIn

0.55

 intptr

0.54

Activations Density 0.285%

technical jargon related to software or systems operations

No Comments

No Known Activations