INDEX

Explanations

discussions surrounding suggestions or proposals in the context of coding or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

()");

-0.57

cendental

-0.53

Rüyada

-0.52

lamabad

-0.52

kháu

-0.52

λιο

-0.52

Выбор

-0.51

noinspection

-0.51

Fazit

-0.49

Portail

-0.49

POSITIVE LOGITS

Did

0.91

Did

0.89

MessageOf

0.75

did

0.74

 nakalista

0.74

NameInMap

0.74

 >=",

0.72

 please

0.72

 Could

0.71

did

0.70

Activations Density 0.302%

discussions surrounding suggestions or proposals in the context of coding or issues

No Comments

No Known Activations