INDEX

Explanations

references to expertise and expert opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ագրություններ

-0.73

}{@

-0.70

parsedMessage

-0.68

ancier

-0.59

########.

-0.59

 albicans

-0.57

sticks

-0.56

ьаж

-0.55

ClCompile

-0.53

WebServlet

-0.52

POSITIVE LOGITS

 opinion

0.77

 AssemblyCulture

0.71

 advice

0.70

 opinions

0.69

 Opinion

0.67

 ✭✭

0.65

 knowledge

0.64

Opinion

0.63

opinion

0.63

 Advice

0.61

Activations Density 0.049%

references to expertise and expert opinions

No Comments

No Known Activations