INDEX

Explanations

user queries and responses related to research or inquiry

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Infórmanos

-0.59

 devoirs

-0.51

țial

-0.51

 mahdol

-0.50

ArrowToggle

-0.50

 <=",

-0.49

цездатний

-0.48

 cordes

-0.48

AnchorStyles

-0.48

 posibil

-0.48

POSITIVE LOGITS

 anywhere

0.71

anywhere

0.65

 nowadays

0.62

 Anywhere

0.60

Hoje

0.59

SetItem

0.59

onViewCreated

0.58

writeFieldEnd

0.57

everywhere

0.56

 CreateTagHelper

0.55

Activations Density 0.308%

user queries and responses related to research or inquiry

No Comments

No Known Activations