INDEX

Explanations

concepts related to data analysis and understanding human experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

[])

-0.66

++

-0.60

 groaned

-0.60

 ويكيپيديا

-0.59

tableFuture

-0.59

:]:

-0.59

[]

-0.58

//});

-0.57

=$?

-0.57

"]);

-0.57

POSITIVE LOGITS

 "..\..\..\

0.49

 estekak

0.47

 برانيه

0.45

出版年

0.45

 "..\..\

0.44

وند

0.44

ánchez

0.44

 webdriver

0.44

Wib

0.43

onAttach

0.43

Activations Density 0.661%

concepts related to data analysis and understanding human experiences

No Comments

No Known Activations