INDEX

Explanations

connections between ideas and highlight important details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Capa

-0.69

 readline

-0.54

fpm

-0.53

tsd

-0.53

 pete

-0.52

chette

-0.52

 Patro

-0.51

échange

-0.50

athread

-0.50

dej

-0.50

POSITIVE LOGITS

GraphicsUnit

0.76

 createState

0.72

DockStyle

0.69

 AssemblyTitle

0.69

Geplaatst

0.68

Datuak

0.66

BeginContext

0.66

 BoxDecoration

0.65

expandindo

0.65

HasIndex

0.64

Activations Density 0.340%

connections between ideas and highlight important details

No Comments

No Known Activations