INDEX

Explanations

references to spiritual or religious concepts related to personal identity and community

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

期的

-0.49

위

-0.47

nter

-0.46

 range

-0.45

ges

-0.45

out

-0.45

 real

-0.45

Sic

-0.43

 consult

-0.43

 content

-0.42

POSITIVE LOGITS

GraphicsUnit

1.07

Personendaten

0.87

 autorytatywna

0.85

 AssemblyCulture

0.85

#+#

0.85

ItemBackground

0.84

KURZBESCHREIBUNG

0.81

WriteTagHelper

0.80

 оригіналу

0.78

 TextAppearance

0.77

Activations Density 0.410%

references to spiritual or religious concepts related to personal identity and community

No Comments

No Known Activations