INDEX

Explanations

terms related to states and processes, particularly in a technical or programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

so

-0.60

-0.58

 part

-0.52

he

-0.50

-0.49

if

-0.49

-0.48

we

-0.48

 that

-0.47

POSITIVE LOGITS

 myſelf

1.33

 itſelf

1.30

 kasarigan

1.20

verwijspagina

1.13

 themſelves

1.11

Portail

1.10

ſelf

1.09

ſelves

1.08

 houſe

1.08

 whoſe

1.06

Activations Density 2.138%

terms related to states and processes, particularly in a technical or programming context

No Comments

No Known Activations