INDEX

Explanations

references to single entities or concepts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 "..\..\

-0.82

 AssemblyCompany

-0.77

 "..\..\..\

-0.71

 kaarangay

-0.63

__(/*!

-0.62

()?;

-0.62

complexType

-0.61

ValueStyle

-0.60

 essayé

-0.60

 bezeichneter

-0.60

POSITIVE LOGITS

 single

1.07

 SINGLE

1.05

 Single

1.00

 solitary

0.99

Single

0.97

SINGLE

0.95

ChildScrollView

0.91

single

0.88

handedly

0.86

getSingle

0.85

Activations Density 0.091%

references to single entities or concepts in various contexts

No Comments

No Known Activations