INDEX

Explanations

specific dates or time periods

oai_token-act-pair · gpt-3.5-turbo

references to historical timelines or dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

queue

-0.77

olulu

-0.76

anooga

-0.76

eye

-0.76

ucky

-0.76

ername

-0.75

ktop

-0.75

orry

-0.75

chester

-0.73

fters

-0.70

POSITIVE LOGITS

 Dating

0.87

 antiquity

0.74

graded

0.70

dated

0.69

 dating

0.69

 antique

0.67

icity

0.67

 Antiqu

0.64

dating

0.63

 dated

0.63

Activations Density 0.025%

specific dates or time periods

references to historical timelines or dates

No Comments

No Known Activations