INDEX

Explanations

conversational elements and dialogue markers in spoken exchanges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 فريبيس

-1.11

 '\\;'

-0.82

featureID

-0.74

aarrggbb

-0.74

 himſelf

-0.71

 itſelf

-0.71

ſy

-0.71

ſelves

-0.69

 BRARY

-0.69

RenderAtEndOf

-0.68

POSITIVE LOGITS

Yeah

0.67

Yes

0.65

 Yeah

0.62

yes

0.62

Yes

0.59

Oh

0.59

 yeah

0.57

 voyez

0.55

Absolutely

0.54

Oh

0.54

Activations Density 0.060%

conversational elements and dialogue markers in spoken exchanges

No Comments

No Known Activations