INDEX

Explanations

emotional expressions and reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.18.hook_mlp_out

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

 متعلقه

-1.09

UnknownFieldSet

-0.60

 تضيفلها

-0.60

/******/

-0.58

Numerology

-0.57

bildning

-0.56

 gratuite

-0.56

 Salgado

-0.55

Grá

-0.55

抜

-0.54

POSITIVE LOGITS

EDEFAULT

0.59

 autorytatywna

0.56

invokeLater

0.55

twimg

0.51

tagext

0.51

DIPSETTING

0.47

 otomatig

0.47

Obi

0.45

发表于

0.45

eyes

0.44

Activations Density 0.040%

emotional expressions and reactions

No Comments

No Known Activations