INDEX

Explanations

the usage of memory-related functions and their arguments

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

LookAnd

-0.71

addCriterion

-0.63

\"]

-0.63

ukone

-0.62

indelijk

-0.62

"",

-0.60

 lyre

-0.60

Sre

-0.60

mybatisplus

-0.60

ArrowToggle

-0.60

POSITIVE LOGITS

 sizeof

3.03

sizeof

3.03

nameof

1.07

 nameof

0.94

offsetof

0.93

typeof

0.87

setof

0.85

 typeof

0.77

 AssemblyTitle

0.71

ChildScrollView

0.66

Activations Density 0.033%

the usage of memory-related functions and their arguments

No Comments

No Known Activations