INDEX

Explanations

statements or questions concerning the topic at hand

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

')")

-0.69

 manières

-0.68

featureID

-0.66

RectangleBorder

-0.65

">',

-0.65

 Psyche

-0.65

 ProductService

-0.64

'>";

-0.62

Πηγές

-0.61

FieldBuilder

-0.61

POSITIVE LOGITS

 maybe

0.54

 الحره

0.53

次は

0.53

жели

0.51

StartsWith

0.50

比如

0.50

前は

0.49

なら

0.48

不如

0.48

̣ng

0.48

Activations Density 0.174%

statements or questions concerning the topic at hand

No Comments

No Known Activations