INDEX

Explanations

references to specific events or outcomes in a sequence of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 utafitiHapana

-0.63

-0.46

timmung

-0.45

 Valera

-0.44

Przypisy

-0.44

paddingVertical

-0.43

ORM

-0.43

 OMIT

-0.41

htdocs

-0.41

 Karma

-0.41

POSITIVE LOGITS

 jScrollPane

0.69

 NSCoder

0.66

 fhort

0.62

Personendaten

0.62

 &___

0.61

 насељу

0.61

 كومونز

0.61

 оригіналу

0.61

StackNavigator

0.61

发表于

0.61

Activations Density 0.336%

references to specific events or outcomes in a sequence of time

No Comments

No Known Activations