INDEX

Explanations

structured data representations, particularly those involving labeled objects and nested data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ors

-0.71

 TextAppearance

-0.71

tics

-0.67

 FontWeight

-0.64

IDATE

-0.62

nesse

-0.60

 estimés

-0.59

de

-0.59

ət

-0.55

mente

-0.55

POSITIVE LOGITS

={

1.21

 autorytatywna

1.17

]={

0.92

InjectAttribute

0.90

={[

0.85

<%=

0.85

 cref

0.84

 Cubans

0.83

 AssemblyTitle

0.82

waf

0.81

Activations Density 0.021%

structured data representations, particularly those involving labeled objects and nested data structures

No Comments

No Known Activations