INDEX

Explanations

years mentioned in specific contexts

oai_token-act-pair · gpt-3.5-turbo

specific years and significant events associated with those years

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

acci

-0.73

 maple

-0.62

 Manufacturer

-0.62

abilia

-0.59

icone

-0.59

 diaper

-0.57

 Sins

-0.57

bip

-0.57

 baking

-0.57

 tire

-0.56

POSITIVE LOGITS

AMY

0.73

 Nicol

0.73

 developments

0.71

GV

0.71

Edu

0.68

IVERS

0.67

BILL

0.64

UTERS

0.64

 Gins

0.64

Guard

0.63

Activations Density 0.243%

years mentioned in specific contexts

specific years and significant events associated with those years

No Comments

No Known Activations