INDEX

Explanations

words and phrases related to expectations and potential outcomes within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Hentet

-0.48

issaient

-0.45

կ

-0.45

 without

-0.44



-0.43

try

-0.43

дован

-0.43

Published

-0.42

nî

-0.42

ensement

-0.40

POSITIVE LOGITS

 ExecuteAsync

0.80

]--;

0.77

 uſe

0.68

 GetEnumerator

0.66

 Bedarf

0.66

 demand

0.63

 myſelf

0.61

 needs

0.61

 auffi

0.61

 neceff

0.61

Activations Density 0.691%

words and phrases related to expectations and potential outcomes within a context

No Comments

No Known Activations