INDEX

Explanations

dates formatted in a specific way

oai_token-act-pair · gpt-3.5-turbo

references to numerical data and statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Contents

-0.82

 è£ıè

-0.79

 Flavoring

-0.75

ophen

-0.71

natureconservancy

-0.65

 contiguous

-0.62

fml

-0.60

 ingred

-0.60

estate

-0.59

 illum

-0.59

POSITIVE LOGITS

PsyNetMessage

0.77

cent

0.69

ruary

0.69

reviewed

0.67

aretz

0.66

eger

0.65

0.64

Activations Density 0.249%

dates formatted in a specific way

references to numerical data and statistical information

No Comments

No Known Activations