INDEX

Explanations

abstract content or sections within documents

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Figure

-0.56

ENGER

-0.54

 ujednoznacz

-0.54

badi

-0.52

ret

-0.49

pieces

-0.49

Figure

-0.49

Sib

-0.49

utex

-0.49

POSITIVE LOGITS

CloseOperation

0.83

 internetowa

0.69

 raiſ

0.65

HasKey

0.65

 placent

0.64

 spirituale

0.63

 Roskov

0.62

 Económica

0.62

SpringBootTest

0.61

contentLoaded

0.61

Activations Density 0.031%

abstract content or sections within documents

No Comments

No Known Activations