INDEX

Explanations

string-related content and formatting details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

DataAnnotations

-0.66

 समीक्षाओं

-0.57

UserScript

-0.56

 protoimpl

-0.56

Aiheesta

-0.53

RTEE

-0.53

#+#

-0.53

 NSError

-0.52

handleRequest

-0.52

TagMode

-0.52

POSITIVE LOGITS

publ

0.48

]}

0.46

IBOutlet

0.46

 Galeria

0.45

gående

0.44

brokes

0.44

akuan

0.44

zaamheid

0.43

 -->>

0.43

 particuli

0.43

Activations Density 0.040%

string-related content and formatting details

No Comments

No Known Activations