INDEX

Explanations

references to initiatives and their related measures or actions

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

-0.69

ن

-0.69

My

-0.67

IANGLES

-0.62

createCell

-0.60

MY

-0.59

isbury

-0.59

uerto

-0.58

 Perkins

-0.58

 Hilton

-0.57

POSITIVE LOGITS

 initiatives

1.06

 initiative

1.04

 themſelves

0.98

 Initiative

0.97

Initiative

0.97

 Schemes

0.96

Measures

0.96

CGA

0.96

measures

0.94

 measures

0.93

Activations Density 0.088%

references to initiatives and their related measures or actions

No Comments

No Known Activations