INDEX

Explanations

terms related to programming structures and functions, particularly those associated with modules and threading

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

WriteBarrier

-0.71

httphttps

-0.66

 protoimpl

-0.64

ChildScrollView

-0.64

parsedMessage

-0.61

 Administrativna

-0.61

 propOrder

-0.59

 pinulongan

-0.59

HttpServlet

-0.57

EditorBrowsable

-0.57

POSITIVE LOGITS

ID

0.89

Name

0.77

ID

0.74

id

0.74

name

0.74

 name

0.72

Id

0.69

 Name

0.64

名

0.64

Def

0.61

Activations Density 0.812%

terms related to programming structures and functions, particularly those associated with modules and threading

No Comments

No Known Activations