INDEX

Explanations

concepts related to principles and observations in scientific or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

udessa

-0.55

 سكانية

-0.49

endpush

-0.49

 dalamnya

-0.48

 statt

-0.48

cjon

-0.48

nodoc

-0.48

 فريبيس

-0.48

 lakukan

-0.47

 rispetto

-0.46

POSITIVE LOGITS

 polega

0.72

 that

0.72

 idea

0.69

invokeLater

0.67

 notion

0.67

InjectAttribute

0.66

WaitGroup

0.65

idea

0.65

postsleuth

0.64

 commandment

0.64

Activations Density 0.668%

concepts related to principles and observations in scientific or legal contexts

No Comments

No Known Activations