INDEX

Explanations

terms related to cases, choices, and conditions within a business context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Monfieur

-1.41

 myſelf

-1.28

 itſelf

-1.26

 betweenstory

-1.24

 themſelves

-1.19

Efq

-1.11

 Theſe

-1.11

ſelves

-1.09

ſelf

-1.07

 houſe

-1.06

POSITIVE LOGITS

$\

0.61

...

0.61

…

0.59

0.58

val

0.58

0.57

to

0.55

<eos>

0.55

Activations Density 1.106%

terms related to cases, choices, and conditions within a business context

No Comments

No Known Activations