INDEX

Explanations

specific identifiers and variables associated with data structures in programming or analysis contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

<bos>

-0.83

HasBeenSet

-0.73

intios

-0.67

 للاسماء

-0.61

addGroup

-0.59

 typelib

-0.57

 Baillargeon

-0.55

 armar

-0.54

AxisAlignment

-0.54

Jeografia

-0.53

POSITIVE LOGITS

примеча

0.62

 Pert

0.60

glBegin

0.55

 contextLoads

0.54

*++

0.52

medriver

0.52

usermodel

0.52

Pert

0.51

setopt

0.51

 maxY

0.50

Activations Density 0.906%

specific identifiers and variables associated with data structures in programming or analysis contexts

No Comments

No Known Activations