INDEX

Explanations

the words that are strongly emphasized or endorsed

oai_token-act-pair · gpt-3.5-turbo

expressions of strong belief or endorsement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oleon

-0.76

 Settlement

-0.76

 Victims

-0.74

 Procedure

-0.73

 Thumbnails

-0.69

illary

-0.68

arters

-0.68

 Chaser

-0.68

 Journals

-0.67

 Millennium

-0.67

POSITIVE LOGITS

 enough

0.88

 recommend

0.87

 discouraged

0.84

 disagree

0.83

 encouraged

0.81

 advised

0.81

 advise

0.81

 correlated

0.79

 discour

0.79

 appreciated

0.78

Activations Density 0.014%

the words that are strongly emphasized or endorsed

expressions of strong belief or endorsement

No Comments

No Known Activations