INDEX

Explanations

dimensions and measurements related to objects

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

 يتيمه

-0.55

hian

-0.47

ultuous

-0.45

 olacaktır

-0.45

 než

-0.44

Prod

-0.43

stine

-0.42

ULAS

-0.42

صال

-0.41

kus

-0.40

POSITIVE LOGITS

DataContract

0.81

ResponseWriter

0.77

 betweenstory

0.72

 esternos

0.71

 متعلقه

0.68

 gynhyrchwyd

0.68

 Wikimedijinoj

0.66

 onBind

0.65

parsedMessage

0.64

 defaultstate

0.63

Activations Density 0.309%

dimensions and measurements related to objects

No Comments

No Known Activations