INDEX

Explanations

phrases relating to uncertainty and inquiries about qualifications or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

awtextra

-0.51

 autorytatywna

-0.49

webElementXpaths

-0.49

 ModelRenderer

-0.48

帖最后由

-0.47

 հղումներ

-0.43

 casada

-0.43

#+#

-0.43

AddTagHelper

-0.42

IBOutlet

-0.41

POSITIVE LOGITS

 neither

0.46

还未

0.45

any

0.44

 whether

0.44

 unknown

0.44

 however

0.43

 details

0.43

yet

0.41

 explicitly

0.40

 specifics

0.40

Activations Density 1.082%

phrases relating to uncertainty and inquiries about qualifications or events

No Comments

No Known Activations