INDEX

Explanations

technical terms and jargon related to systems and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.97

AddTagHelper

-0.85

OGND

-0.79

ArgsConstructor

-0.79

 EconPapers

-0.77

queryInterface

-0.75

 pinulongan

-0.73

awtextra

-0.72

JspWriter

-0.71

 MainAxisSize

-0.70

POSITIVE LOGITS

 same

0.50

__

0.48

 also

0.47

 aussi

0.44

(()

0.44

niej

0.43

něž

0.43

 mostly

0.42

پور

0.42

 Zusammenhang

0.42

Activations Density 2.031%

technical terms and jargon related to systems and processes

No Comments

No Known Activations