INDEX

Explanations

references to business practices and financial metrics in a detailed explanatory context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

CodedInputStream

-0.57

ständ

-0.54

fjspx

-0.54

 anbef

-0.52

extAlignment

-0.52

спита

-0.50

RepeatedField

-0.50

 radix

-0.49

latego

-0.49

ActionCreators

-0.49

POSITIVE LOGITS

but

0.58

BoxShadow

0.55

but

0.50

Билгалдахарш

0.48

Identyfik

0.48

 ولك

0.47

apist

0.47

 pinulongan

0.46

ziale

0.46

WriteAttribute

0.46

Activations Density 0.465%

references to business practices and financial metrics in a detailed explanatory context

No Comments

No Known Activations