INDEX

Explanations

phrases related to requests and requirements

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

 mesmos

-0.47

-0.43

 Kohn

-0.42

reme

-0.41

an

-0.41

 että

-0.40

avir

-0.40

πως

-0.40

didReceive

-0.40

viale

-0.38

POSITIVE LOGITS

 InputDecoration

0.78

 Anſ

0.73

 JpaRepository

0.72

 raiſ

0.69

]")]

0.68

0.67

Efq

0.66

 Monfieur

0.65

 otomatig

0.64

 adequately

0.63

Activations Density 0.300%

phrases related to requests and requirements

No Comments

No Known Activations