INDEX

Explanations

elements related to structured data or formatted text representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 CreateTagHelper

-0.65

 ExecuteAsync

-0.62

 paramString

-0.61

"</

-0.58

RunAsync

-0.58

%";

-0.57

"]}

-0.56

SBATCH

-0.55

----</

-0.54

denas

-0.54

POSITIVE LOGITS

MENAFN

0.64

subpackage

0.64

<u>

0.63

 "..\..\

0.59

Viitteet

0.56

BufferException

0.53

 nakalista

0.53

EDEFAULT

0.53

 Савезне

0.52

AnchorTagHelper

0.52

Activations Density 0.065%

elements related to structured data or formatted text representations

No Comments

No Known Activations