INDEX

Explanations

references to scientific publications and academic terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 المعيارى

-0.62

intios

-0.52

<bos>

-0.47

bonucleic

-0.47

edig

-0.46

krut

-0.46

carpus

-0.46

erst

-0.45

="{{

-0.45

 Scherer

-0.45

POSITIVE LOGITS

 myſelf

0.74

 itſelf

0.73

 themſelves

0.69

 contextLoads

0.68

ientôt

0.67

ſelves

0.67

."],

0.66

 poffible

0.66

 Jenner

0.66

 buffalo

0.65

Activations Density 2.713%

references to scientific publications and academic terminology

No Comments

No Known Activations