INDEX

Explanations

technical specifications and measurements related to hardware components

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

the

-0.50

of

-0.47

izr

-0.47

 during

-0.47

getSimpleName

-0.47

 possíveis

-0.44

 always

-0.44

 just

-0.44

hradun

-0.44

enheim

-0.43

POSITIVE LOGITS

 Shakspeare

0.80

 AssemblyTitle

0.72

 Shaksp

0.65

 leaſt

0.64

 leaft

0.61

olesale

0.61

 Majefty

0.61

 StringVar

0.61

ContentLoaded

0.60

 ſmall

0.58

Activations Density 0.295%

technical specifications and measurements related to hardware components

No Comments

No Known Activations