INDEX

Explanations

references to graphs or graphical representations in scientific texts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PendingIntent

-0.98

ContentLoaded

-0.82

########.

-0.78

 Gracie

-0.77

 Bree

-0.76

 Maren

-0.76

 PackageManager

-0.75

ActivityCompat

-0.73

 समीक्षाओं

-0.73

 Leno

-0.72

POSITIVE LOGITS

 Graph

1.15

 graphene

1.13

 graphs

1.05

 Graphs

1.05

Graph

1.02

Graphs

1.02

graphs

1.00

GRAPH

0.94

 graph

0.92

 graphing

0.88

Activations Density 0.011%

references to graphs or graphical representations in scientific texts

No Comments

No Known Activations