INDEX

Explanations

words related to various forms of media and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.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

NoSuchAlgorithm

-0.47

RTEX

-0.47

ệc

-0.44

 prop

-0.44

atiker

-0.43

Brainz

-0.43

Matched

-0.42

 Definition

-0.41

 perintah

-0.41

ActivityCompat

-0.41

POSITIVE LOGITS

ագրություններ

0.95

 nakalista

0.81

ValueStyle

0.74

NameInMap

0.72

########.

0.72

CPtr

0.70

 autorytatywna

0.70

ⓧ

0.69

principalColumn

0.69

enumi

0.69

Activations Density 0.167%

words related to various forms of media and their classifications

No Comments

No Known Activations