INDEX

Explanations

phrases or references that indicate a process or requirement in a technical context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defStyle

-0.71

 Wikimedijinoj

-0.63

FieldNumber

-0.60

 forsø

-0.57

новниш

-0.56

alogy

-0.56

 vilá

-0.55

 genoux

-0.55

alnız

-0.54

Itoa

-0.54

POSITIVE LOGITS

 المعيارى

0.63

encodeWith

0.59

 their

0.55

 individual

0.54

ivat

0.54

offsetof

0.54

lardır

0.54

 additional

0.52

 relevant

0.52

 MonoBehaviour

0.52

Activations Density 0.632%

phrases or references that indicate a process or requirement in a technical context

No Comments

No Known Activations