INDEX

Explanations

terms related to users and their interactions in various contexts

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

Öffnungszeiten

-0.48

+",

-0.45

|}{$

-0.44

⊗

-0.44

abandoned

-0.44

tabak

-0.44

 onBind

-0.44

currentColor

-0.43

compañ

-0.43

EndProject

-0.43

POSITIVE LOGITS

 تضيفلها

0.79

djangoproject

0.71

 FetchType

0.68

principalColumn

0.66

 trajets

0.65

 استنادى

0.61

 الرخصة

0.60

تقاوى

0.58

PropertyGroup

0.58

ValueStyle

0.56

Activations Density 0.450%

terms related to users and their interactions in various contexts

No Comments

No Known Activations