INDEX

Explanations

references to specific cases and studies, as well as phrases indicating knowledge or familiarity with a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

CppMethod

-0.72

 AppBar

-0.65

IsPostBack

-0.64

!*\

-0.64

PerformLayout

-0.63

 Waray

-0.62

HttpPut

-0.61

-0.60

IsContent

-0.58

 оригіналу

-0.58

POSITIVE LOGITS

SourceChecksum

0.61

DockStyle

0.57

Datuak

0.57

见过

0.54

Бележки

0.52

portál

0.51

 clearColor

0.50

룹

0.48

writerow

0.48

idosis

0.48

Activations Density 0.315%

references to specific cases and studies, as well as phrases indicating knowledge or familiarity with a topic

No Comments

No Known Activations