INDEX

Explanations

sections of text with no activations, indicating it is not detecting any specific content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 transfieras

-0.68

&_

-0.53

thâu

-0.52

 plötzlich

-0.51

ठी

-0.51

optarg

-0.50

 poteva

-0.50

 مشين

-0.50

Havolalar

-0.49

 lacked

-0.49

POSITIVE LOGITS

 möglichst

0.63

 provide

0.60

 someday

0.55

 every

0.53

 inspire

0.53

 empower

0.51

 improve

0.51

能让

0.51

phylo

0.50

尽可能

0.50

Activations Density 0.221%

sections of text with no activations, indicating it is not detecting any specific content

No Comments

No Known Activations